Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1675 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4474. Min Range: -12.4474
Max Act: 12.4474. Min Act: -0.1700
Data Index: 3551582 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4474. Min Range: -12.4474
Max Act: 12.1349. Min Act: -0.1700
Data Index: 7159243 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4474. Min Range: -12.4474
Max Act: 12.0099. Min Act: -0.1700
Data Index: 1521275 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4474. Min Range: -12.4474
Max Act: 12.0099. Min Act: -0.1700
Data Index: 2004125 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4474. Min Range: -12.4474
Max Act: 11.8849. Min Act: -0.1700
Data Index: 3994049 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4474. Min Range: -12.4474
Max Act: 11.7599. Min Act: -0.1700
Data Index: 5825205 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4474. Min Range: -12.4474
Max Act: 11.8224. Min Act: -0.1700
Data Index: 7743925 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4474. Min Range: -12.4474
Max Act: 11.7599. Min Act: -0.1700
Data Index: 2870537 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4474. Min Range: -12.4474
Max Act: 11.6974. Min Act: -0.1700
Data Index: 4558719 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4474. Min Range: -12.4474
Max Act: 11.6974. Min Act: -0.1700
Data Index: 1080656 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4474. Min Range: -12.4474
Max Act: 11.5724. Min Act: -0.1700
Data Index: 3507540 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4474. Min Range: -12.4474
Max Act: 11.5724. Min Act: -0.1700
Data Index: 6477802 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4474. Min Range: -12.4474
Max Act: 11.5724. Min Act: -0.1700
Data Index: 693419 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4474. Min Range: -12.4474
Max Act: 11.5099. Min Act: -0.1700
Data Index: 7768457 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4474. Min Range: -12.4474
Max Act: 11.5099. Min Act: -0.1700
Data Index: 215781 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4474. Min Range: -12.4474
Max Act: 11.5099. Min Act: -0.1700
Data Index: 2441980 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4474. Min Range: -12.4474
Max Act: 11.4474. Min Act: -0.1700
Data Index: 1906145 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4474. Min Range: -12.4474
Max Act: 11.4474. Min Act: -0.1700
Data Index: 1966194 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4474. Min Range: -12.4474
Max Act: 11.4474. Min Act: -0.1700
Data Index: 8420698 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4474. Min Range: -12.4474
Max Act: 11.3224. Min Act: -0.1700
Data Index: 2536578 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19