Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4596 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1216. Min Range: -3.1216
Max Act: 3.1216. Min Act: -0.1700
Data Index: 8202806 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1216. Min Range: -3.1216
Max Act: 3.0586. Min Act: -0.1700
Data Index: 8598007 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1216. Min Range: -3.1216
Max Act: 3.0270. Min Act: -0.1700
Data Index: 1160819 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1216. Min Range: -3.1216
Max Act: 3.0428. Min Act: -0.1700
Data Index: 2393110 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1216. Min Range: -3.1216
Max Act: 2.9796. Min Act: -0.1700
Data Index: 7512558 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1216. Min Range: -3.1216
Max Act: 2.9638. Min Act: -0.1700
Data Index: 752880 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1216. Min Range: -3.1216
Max Act: 2.9480. Min Act: -0.1700
Data Index: 922173 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1216. Min Range: -3.1216
Max Act: 2.9480. Min Act: -0.1700
Data Index: 1705509 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1216. Min Range: -3.1216
Max Act: 2.9480. Min Act: -0.1700
Data Index: 5869862 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1216. Min Range: -3.1216
Max Act: 2.9321. Min Act: -0.1700
Data Index: 2811885 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1216. Min Range: -3.1216
Max Act: 2.9321. Min Act: -0.1700
Data Index: 1962418 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1216. Min Range: -3.1216
Max Act: 2.9321. Min Act: -0.1700
Data Index: 6526543 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1216. Min Range: -3.1216
Max Act: 2.9163. Min Act: -0.1700
Data Index: 4912365 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1216. Min Range: -3.1216
Max Act: 2.9004. Min Act: -0.1700
Data Index: 6153783 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1216. Min Range: -3.1216
Max Act: 2.9004. Min Act: -0.1700
Data Index: 8718365 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1216. Min Range: -3.1216
Max Act: 2.8846. Min Act: -0.1700
Data Index: 8060249 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1216. Min Range: -3.1216
Max Act: 2.9004. Min Act: -0.1700
Data Index: 6741283 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1216. Min Range: -3.1216
Max Act: 2.8846. Min Act: -0.1700
Data Index: 983457 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1216. Min Range: -3.1216
Max Act: 2.8687. Min Act: -0.1700
Data Index: 5952885 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1216. Min Range: -3.1216
Max Act: 2.8687. Min Act: -0.1700
Data Index: 6237235 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19