Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.4890. Min Act: -0.1700
Data Index: 8721798 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.3793. Min Act: -0.1700
Data Index: 484781 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.2537. Min Act: -0.1700
Data Index: 1746311 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.2223. Min Act: -0.1700
Data Index: 2590040 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.1908. Min Act: -0.1700
Data Index: 7340275 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.1751. Min Act: -0.1700
Data Index: 3385917 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.1751. Min Act: -0.1700
Data Index: 3434547 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.1594. Min Act: -0.1700
Data Index: 8124898 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.1436. Min Act: -0.1700
Data Index: 1920208 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.1436. Min Act: -0.1700
Data Index: 4075498 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.1279. Min Act: -0.1700
Data Index: 6350051 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.1279. Min Act: -0.1700
Data Index: 7575255 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.1279. Min Act: -0.1700
Data Index: 3720606 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.1279. Min Act: -0.1700
Data Index: 6211270 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.1121. Min Act: -0.1700
Data Index: 4513315 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.1121. Min Act: -0.1700
Data Index: 8490201 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.1121. Min Act: -0.1700
Data Index: 5056885 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.1121. Min Act: -0.1700
Data Index: 7238376 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.1121. Min Act: -0.1700
Data Index: 3783176 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4890. Min Range: -3.4890
Max Act: 3.0963. Min Act: -0.1700
Data Index: 198284 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19