Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3385 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.8263. Min Act: -0.1700
Data Index: 1985035 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.7951. Min Act: -0.1700
Data Index: 8601950 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.7638. Min Act: -0.1700
Data Index: 7159417 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.6701. Min Act: -0.1700
Data Index: 4708297 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.6076. Min Act: -0.1700
Data Index: 1154772 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.6388. Min Act: -0.1700
Data Index: 3425168 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.6076. Min Act: -0.1700
Data Index: 2685808 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.5763. Min Act: -0.1700
Data Index: 2977505 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.5763. Min Act: -0.1700
Data Index: 3739348 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.5138. Min Act: -0.1700
Data Index: 489571 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.4513. Min Act: -0.1700
Data Index: 2992839 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.4201. Min Act: -0.1700
Data Index: 8522211 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.4201. Min Act: -0.1700
Data Index: 8574366 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.4201. Min Act: -0.1700
Data Index: 8386855 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.3888. Min Act: -0.1700
Data Index: 3285413 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.3888. Min Act: -0.1700
Data Index: 2234918 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.3576. Min Act: -0.1700
Data Index: 7678150 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.3263. Min Act: -0.1700
Data Index: 3459703 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.3263. Min Act: -0.1700
Data Index: 8285918 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8263. Min Range: -5.8263
Max Act: 5.2951. Min Act: -0.1700
Data Index: 2196288 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19