Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2175. Min Range: -7.2175
Max Act: 7.2175. Min Act: -0.1700
Data Index: 8471900 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2175. Min Range: -7.2175
Max Act: 7.1550. Min Act: -0.1700
Data Index: 4127394 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2175. Min Range: -7.2175
Max Act: 7.1238. Min Act: -0.1700
Data Index: 2225142 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.9363. Min Act: -0.1700
Data Index: 4871444 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.9363. Min Act: -0.1700
Data Index: 4941505 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.9050. Min Act: -0.1700
Data Index: 1405192 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.9363. Min Act: -0.1700
Data Index: 5470214 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.9050. Min Act: -0.1700
Data Index: 325639 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.8738. Min Act: -0.1700
Data Index: 5487814 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.9050. Min Act: -0.1700
Data Index: 8202351 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.8425. Min Act: -0.1700
Data Index: 2709965 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.8425. Min Act: -0.1700
Data Index: 2723445 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.8425. Min Act: -0.1700
Data Index: 3628457 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.7488. Min Act: -0.1700
Data Index: 2170108 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.7488. Min Act: -0.1700
Data Index: 6892266 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.7488. Min Act: -0.1700
Data Index: 4465029 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.7175. Min Act: -0.1700
Data Index: 6487967 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.6863. Min Act: -0.1700
Data Index: 7490202 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.6550. Min Act: -0.1700
Data Index: 2294751 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2175. Min Range: -7.2175
Max Act: 6.6863. Min Act: -0.1700
Data Index: 1170427 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19