Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4345 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0459. Min Range: -6.0459
Max Act: 6.0459. Min Act: -0.1700
Data Index: 8765765 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0459. Min Range: -6.0459
Max Act: 6.0459. Min Act: -0.1700
Data Index: 803145 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.9834. Min Act: -0.1700
Data Index: 2959548 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.9521. Min Act: -0.1700
Data Index: 7044065 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.8584. Min Act: -0.1700
Data Index: 3140013 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.8271. Min Act: -0.1700
Data Index: 3727354 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.8271. Min Act: -0.1700
Data Index: 7323463 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.7646. Min Act: -0.1700
Data Index: 2203332 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.7646. Min Act: -0.1700
Data Index: 8030089 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.7646. Min Act: -0.1700
Data Index: 3116651 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.7334. Min Act: -0.1700
Data Index: 2958326 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.7334. Min Act: -0.1700
Data Index: 1915904 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.7021. Min Act: -0.1700
Data Index: 1109070 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.7021. Min Act: -0.1700
Data Index: 3658293 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.6709. Min Act: -0.1700
Data Index: 8683640 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.7021. Min Act: -0.1700
Data Index: 5757587 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.7021. Min Act: -0.1700
Data Index: 3309134 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.6709. Min Act: -0.1700
Data Index: 3095937 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.6396. Min Act: -0.1700
Data Index: 5534301 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0459. Min Range: -6.0459
Max Act: 5.6084. Min Act: -0.1700
Data Index: 5802833 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19