Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5315 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2293. Min Range: -6.2293
Max Act: 6.2293. Min Act: -0.1700
Data Index: 4447116 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2293. Min Range: -6.2293
Max Act: 6.1981. Min Act: -0.1700
Data Index: 8771886 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2293. Min Range: -6.2293
Max Act: 6.0731. Min Act: -0.1700
Data Index: 6679174 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2293. Min Range: -6.2293
Max Act: 6.0418. Min Act: -0.1700
Data Index: 525785 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2293. Min Range: -6.2293
Max Act: 5.9793. Min Act: -0.1700
Data Index: 2869803 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2293. Min Range: -6.2293
Max Act: 5.9481. Min Act: -0.1700
Data Index: 5896669 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2293. Min Range: -6.2293
Max Act: 5.9481. Min Act: -0.1700
Data Index: 3852632 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2293. Min Range: -6.2293
Max Act: 5.9168. Min Act: -0.1700
Data Index: 6373110 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2293. Min Range: -6.2293
Max Act: 5.8856. Min Act: -0.1700
Data Index: 3901170 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2293. Min Range: -6.2293
Max Act: 5.8543. Min Act: -0.1700
Data Index: 142894 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2293. Min Range: -6.2293
Max Act: 5.8856. Min Act: -0.1700
Data Index: 637352 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2293. Min Range: -6.2293
Max Act: 5.8543. Min Act: -0.1700
Data Index: 8763052 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2293. Min Range: -6.2293
Max Act: 5.8856. Min Act: -0.1700
Data Index: 6559533 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2293. Min Range: -6.2293
Max Act: 5.8543. Min Act: -0.1700
Data Index: 896768 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2293. Min Range: -6.2293
Max Act: 5.7918. Min Act: -0.1700
Data Index: 3170091 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2293. Min Range: -6.2293
Max Act: 5.8231. Min Act: -0.1700
Data Index: 6183061 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2293. Min Range: -6.2293
Max Act: 5.8231. Min Act: -0.1700
Data Index: 49732 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2293. Min Range: -6.2293
Max Act: 5.8231. Min Act: -0.1700
Data Index: 7006813 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2293. Min Range: -6.2293
Max Act: 5.8231. Min Act: -0.1700
Data Index: 7231059 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2293. Min Range: -6.2293
Max Act: 5.8231. Min Act: -0.1700
Data Index: 8602870 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19