Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3191 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6687. Min Range: -7.6687
Max Act: 7.6687. Min Act: -0.1700
Data Index: 5465816 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6687. Min Range: -7.6687
Max Act: 7.6374. Min Act: -0.1700
Data Index: 6976809 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6687. Min Range: -7.6687
Max Act: 7.5437. Min Act: -0.1700
Data Index: 1806169 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6687. Min Range: -7.6687
Max Act: 7.4187. Min Act: -0.1700
Data Index: 34853 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6687. Min Range: -7.6687
Max Act: 7.3874. Min Act: -0.1700
Data Index: 8545066 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6687. Min Range: -7.6687
Max Act: 7.3249. Min Act: -0.1700
Data Index: 5230817 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6687. Min Range: -7.6687
Max Act: 7.2937. Min Act: -0.1700
Data Index: 656833 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6687. Min Range: -7.6687
Max Act: 7.2937. Min Act: -0.1700
Data Index: 231427 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6687. Min Range: -7.6687
Max Act: 7.1999. Min Act: -0.1700
Data Index: 2994652 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6687. Min Range: -7.6687
Max Act: 7.1999. Min Act: -0.1700
Data Index: 1696557 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6687. Min Range: -7.6687
Max Act: 7.0749. Min Act: -0.1698
Data Index: 2702153 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6687. Min Range: -7.6687
Max Act: 7.0749. Min Act: -0.1700
Data Index: 3141422 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6687. Min Range: -7.6687
Max Act: 7.0124. Min Act: -0.1700
Data Index: 6209582 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6687. Min Range: -7.6687
Max Act: 6.9812. Min Act: -0.1700
Data Index: 2130149 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6687. Min Range: -7.6687
Max Act: 6.9499. Min Act: -0.1700
Data Index: 5485481 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6687. Min Range: -7.6687
Max Act: 6.8562. Min Act: -0.1700
Data Index: 4665539 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6687. Min Range: -7.6687
Max Act: 6.9187. Min Act: -0.1700
Data Index: 4171066 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6687. Min Range: -7.6687
Max Act: 6.8874. Min Act: -0.1700
Data Index: 8336999 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6687. Min Range: -7.6687
Max Act: 6.8562. Min Act: -0.1700
Data Index: 8064821 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6687. Min Range: -7.6687
Max Act: 6.7937. Min Act: -0.1699
Data Index: 2027335 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19