Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3814 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0132. Min Range: -6.0132
Max Act: 6.0132. Min Act: -0.1700
Data Index: 229246 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.9194. Min Act: -0.1700
Data Index: 387148 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.6694. Min Act: -0.1700
Data Index: 3599597 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.5757. Min Act: -0.1700
Data Index: 6109060 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.5444. Min Act: -0.1700
Data Index: 2330965 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.4819. Min Act: -0.1700
Data Index: 4071473 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.4819. Min Act: -0.1700
Data Index: 1390862 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.4194. Min Act: -0.1700
Data Index: 1237306 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.4507. Min Act: -0.1700
Data Index: 1954085 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.3882. Min Act: -0.1700
Data Index: 1091937 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.3882. Min Act: -0.1700
Data Index: 3538492 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.3569. Min Act: -0.1700
Data Index: 5464076 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.3569. Min Act: -0.1700
Data Index: 4942668 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.3569. Min Act: -0.1700
Data Index: 3883790 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.3569. Min Act: -0.1700
Data Index: 4079431 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.3569. Min Act: -0.1700
Data Index: 7882898 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.3257. Min Act: -0.1700
Data Index: 4130935 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.2632. Min Act: -0.1700
Data Index: 57857 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.3257. Min Act: -0.1700
Data Index: 4106316 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0132. Min Range: -6.0132
Max Act: 5.2944. Min Act: -0.1700
Data Index: 2128541 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19