Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.9111. Min Act: -0.1700
Data Index: 3798825 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.8174. Min Act: -0.1700
Data Index: 6590846 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.7861. Min Act: -0.1700
Data Index: 3866288 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.7549. Min Act: -0.1700
Data Index: 6486464 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.5049. Min Act: -0.1700
Data Index: 2942419 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.4111. Min Act: -0.1700
Data Index: 276785 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.3799. Min Act: -0.1700
Data Index: 7646535 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.3174. Min Act: -0.1700
Data Index: 4295095 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.3174. Min Act: -0.1700
Data Index: 1669031 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.3174. Min Act: -0.1700
Data Index: 1100039 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.2861. Min Act: -0.1700
Data Index: 1411300 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.2549. Min Act: -0.1700
Data Index: 4329667 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.2236. Min Act: -0.1700
Data Index: 6939566 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.2236. Min Act: -0.1700
Data Index: 8487845 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.1924. Min Act: -0.1700
Data Index: 8124541 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.2236. Min Act: -0.1700
Data Index: 6785912 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.1924. Min Act: -0.1700
Data Index: 7775776 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.1299. Min Act: -0.1700
Data Index: 4002911 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.1611. Min Act: -0.1700
Data Index: 105218 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9111. Min Range: -6.9111
Max Act: 6.1611. Min Act: -0.1700
Data Index: 5419623 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19