Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3415 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.6306. Min Act: -0.1700
Data Index: 3656561 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.3806. Min Act: -0.1700
Data Index: 4352018 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.2556. Min Act: -0.1700
Data Index: 4173595 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.1306. Min Act: -0.1700
Data Index: 8679261 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.1306. Min Act: -0.1700
Data Index: 4345346 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.1306. Min Act: -0.1700
Data Index: 336881 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.0681. Min Act: -0.1700
Data Index: 8472956 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.0369. Min Act: -0.1700
Data Index: 2589897 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.0369. Min Act: -0.1700
Data Index: 2895336 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.0681. Min Act: -0.1700
Data Index: 1254192 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.0994. Min Act: -0.1700
Data Index: 7710709 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.0369. Min Act: -0.1700
Data Index: 2781766 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.0994. Min Act: -0.1700
Data Index: 7749897 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.0369. Min Act: -0.1700
Data Index: 3366550 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.0056. Min Act: -0.1700
Data Index: 408459 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.0056. Min Act: -0.1700
Data Index: 7223226 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6306. Min Range: -6.6306
Max Act: 5.9744. Min Act: -0.1700
Data Index: 1120991 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.0056. Min Act: -0.1700
Data Index: 314263 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6306. Min Range: -6.6306
Max Act: 5.9744. Min Act: -0.1700
Data Index: 7237929 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6306. Min Range: -6.6306
Max Act: 5.9744. Min Act: -0.1700
Data Index: 5216738 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19