Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2460 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.5393. Min Act: -0.1700
Data Index: 5490040 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.5080. Min Act: -0.1700
Data Index: 8371928 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.4296. Min Act: -0.1700
Data Index: 6060672 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.3669. Min Act: -0.1700
Data Index: 2250515 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.3512. Min Act: -0.1700
Data Index: 2871791 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.3355. Min Act: -0.1700
Data Index: 8336013 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.3198. Min Act: -0.1700
Data Index: 4049198 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.3355. Min Act: -0.1700
Data Index: 1436824 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.2727. Min Act: -0.1700
Data Index: 4251012 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.2884. Min Act: -0.1700
Data Index: 1302636 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.2727. Min Act: -0.1700
Data Index: 3711157 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.2727. Min Act: -0.1700
Data Index: 5060854 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.2727. Min Act: -0.1700
Data Index: 431061 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.2413. Min Act: -0.1700
Data Index: 1133236 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.2413. Min Act: -0.1700
Data Index: 5178751 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.2256. Min Act: -0.1700
Data Index: 2193017 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.2413. Min Act: -0.1700
Data Index: 8743769 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.2413. Min Act: -0.1700
Data Index: 2499183 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.2256. Min Act: -0.1700
Data Index: 331602 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5393. Min Range: -3.5393
Max Act: 3.2256. Min Act: -0.1700
Data Index: 5898253 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19