Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3008 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2184. Min Range: -8.2184
Max Act: 8.2184. Min Act: -0.1700
Data Index: 2560452 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2184. Min Range: -8.2184
Max Act: 8.0621. Min Act: -0.1700
Data Index: 8817188 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.8121. Min Act: -0.1700
Data Index: 6892541 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.8121. Min Act: -0.1700
Data Index: 7877671 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.7496. Min Act: -0.1700
Data Index: 3368566 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.7496. Min Act: -0.1700
Data Index: 7555072 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.7496. Min Act: -0.1700
Data Index: 5822861 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.6871. Min Act: -0.1700
Data Index: 5331457 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.5934. Min Act: -0.1700
Data Index: 8337001 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.5934. Min Act: -0.1700
Data Index: 5046460 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.5934. Min Act: -0.1700
Data Index: 3800369 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.6246. Min Act: -0.1700
Data Index: 6442301 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.5621. Min Act: -0.1700
Data Index: 4904212 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.4996. Min Act: -0.1700
Data Index: 762192 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.4996. Min Act: -0.1700
Data Index: 5208102 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.5309. Min Act: -0.1700
Data Index: 2413020 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.4684. Min Act: -0.1700
Data Index: 4372980 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.4371. Min Act: -0.1700
Data Index: 7676219 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.4371. Min Act: -0.1700
Data Index: 742655 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2184. Min Range: -8.2184
Max Act: 7.4059. Min Act: -0.1700
Data Index: 2702348 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19