Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.7112. Min Act: -0.1700
Data Index: 132503 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.6799. Min Act: -0.1700
Data Index: 8197245 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.6487. Min Act: -0.1700
Data Index: 4780900 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.6487. Min Act: -0.1700
Data Index: 5418348 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.6174. Min Act: -0.1700
Data Index: 569182 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.5862. Min Act: -0.1700
Data Index: 3653266 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.5862. Min Act: -0.1700
Data Index: 4706784 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.5862. Min Act: -0.1700
Data Index: 8184939 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.5549. Min Act: -0.1700
Data Index: 4298922 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.5549. Min Act: -0.1700
Data Index: 8277935 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.5237. Min Act: -0.1700
Data Index: 7883311 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.4924. Min Act: -0.1700
Data Index: 6961530 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.4612. Min Act: -0.1700
Data Index: 6195454 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.4612. Min Act: -0.1700
Data Index: 3496023 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.4612. Min Act: -0.1700
Data Index: 5409692 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.4299. Min Act: -0.1700
Data Index: 2731811 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.4612. Min Act: -0.1700
Data Index: 1187283 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.4612. Min Act: -0.1700
Data Index: 6083536 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.4299. Min Act: -0.1700
Data Index: 2515465 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7112. Min Range: -5.7112
Max Act: 5.4299. Min Act: -0.1700
Data Index: 6691120 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19