Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4560 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.5768. Min Act: -0.1700
Data Index: 6739091 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.4518. Min Act: -0.1700
Data Index: 1653592 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.3893. Min Act: -0.1700
Data Index: 5976304 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.4205. Min Act: -0.1700
Data Index: 2893431 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.3893. Min Act: -0.1700
Data Index: 3655054 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.3893. Min Act: -0.1700
Data Index: 235193 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.3580. Min Act: -0.1700
Data Index: 8230054 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.3268. Min Act: -0.1700
Data Index: 6820388 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.3268. Min Act: -0.1700
Data Index: 7087181 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.2955. Min Act: -0.1700
Data Index: 8377229 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.2643. Min Act: -0.1700
Data Index: 1560573 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.3268. Min Act: -0.1700
Data Index: 8600071 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.2330. Min Act: -0.1700
Data Index: 1318728 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.2643. Min Act: -0.1700
Data Index: 7138089 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.2643. Min Act: -0.1700
Data Index: 7672952 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.2643. Min Act: -0.1700
Data Index: 3036602 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.2330. Min Act: -0.1700
Data Index: 1154710 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.2330. Min Act: -0.1700
Data Index: 6729775 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.2330. Min Act: -0.1700
Data Index: 4058326 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5768. Min Range: -4.5768
Max Act: 4.2018. Min Act: -0.1700
Data Index: 2894824 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19