Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3380 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1153. Min Range: -5.1153
Max Act: 5.1153. Min Act: -0.1700
Data Index: 142500 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1153. Min Range: -5.1153
Max Act: 5.0528. Min Act: -0.1700
Data Index: 435497 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1153. Min Range: -5.1153
Max Act: 5.0215. Min Act: -0.1700
Data Index: 47405 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.8965. Min Act: -0.1700
Data Index: 8174365 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.8965. Min Act: -0.1700
Data Index: 8174368 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.8653. Min Act: -0.1700
Data Index: 8174366 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.8340. Min Act: -0.1700
Data Index: 616924 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.8340. Min Act: -0.1700
Data Index: 8174371 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.8340. Min Act: -0.1700
Data Index: 8174364 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.7715. Min Act: -0.1700
Data Index: 1361104 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.7403. Min Act: -0.1700
Data Index: 8174369 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.7403. Min Act: -0.1700
Data Index: 1442483 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.7403. Min Act: -0.1700
Data Index: 5631921 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.7403. Min Act: -0.1700
Data Index: 8174370 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.7090. Min Act: -0.1700
Data Index: 8628882 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.7090. Min Act: -0.1700
Data Index: 8826519 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.6778. Min Act: -0.1700
Data Index: 8191752 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.6778. Min Act: -0.1700
Data Index: 2256146 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.6778. Min Act: -0.1700
Data Index: 8622398 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1153. Min Range: -5.1153
Max Act: 4.6465. Min Act: -0.1700
Data Index: 6596516 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19