Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4191 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.6382. Min Act: -0.1700
Data Index: 7847723 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.6070. Min Act: -0.1700
Data Index: 3537205 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.5757. Min Act: -0.1700
Data Index: 6398639 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.5757. Min Act: -0.1700
Data Index: 6056103 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.5445. Min Act: -0.1700
Data Index: 4260289 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.5445. Min Act: -0.1700
Data Index: 7552109 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.5445. Min Act: -0.1700
Data Index: 6035401 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.5445. Min Act: -0.1700
Data Index: 5866959 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.5445. Min Act: -0.1700
Data Index: 8526730 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.5132. Min Act: -0.1700
Data Index: 1044227 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.5132. Min Act: -0.1700
Data Index: 4121231 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.4820. Min Act: -0.1700
Data Index: 3423782 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.4820. Min Act: -0.1700
Data Index: 7803561 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.4820. Min Act: -0.1699
Data Index: 7504908 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.4820. Min Act: -0.1700
Data Index: 6959103 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.4820. Min Act: -0.1700
Data Index: 2170540 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.4820. Min Act: -0.1700
Data Index: 6947949 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.4507. Min Act: -0.1700
Data Index: 507057 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.4507. Min Act: -0.1698
Data Index: 6197379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6382. Min Range: -4.6382
Max Act: 4.4820. Min Act: -0.1700
Data Index: 1317818 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19