Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4374 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3944. Min Range: -7.3944
Max Act: 7.3944. Min Act: -0.1700
Data Index: 4812944 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3944. Min Range: -7.3944
Max Act: 7.3319. Min Act: -0.1700
Data Index: 5661514 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3944. Min Range: -7.3944
Max Act: 7.3319. Min Act: -0.1700
Data Index: 5101194 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3944. Min Range: -7.3944
Max Act: 7.2382. Min Act: -0.1700
Data Index: 939346 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3944. Min Range: -7.3944
Max Act: 7.2694. Min Act: -0.1700
Data Index: 6768314 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3944. Min Range: -7.3944
Max Act: 7.1757. Min Act: -0.1700
Data Index: 3451968 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3944. Min Range: -7.3944
Max Act: 7.1444. Min Act: -0.1700
Data Index: 7142091 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3944. Min Range: -7.3944
Max Act: 7.1757. Min Act: -0.1700
Data Index: 4402318 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3944. Min Range: -7.3944
Max Act: 7.0507. Min Act: -0.1700
Data Index: 8781598 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3944. Min Range: -7.3944
Max Act: 7.0507. Min Act: -0.1700
Data Index: 1402175 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3944. Min Range: -7.3944
Max Act: 7.0507. Min Act: -0.1700
Data Index: 2371182 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3944. Min Range: -7.3944
Max Act: 7.0194. Min Act: -0.1700
Data Index: 5091894 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3944. Min Range: -7.3944
Max Act: 6.9882. Min Act: -0.1700
Data Index: 8551579 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3944. Min Range: -7.3944
Max Act: 6.8944. Min Act: -0.1700
Data Index: 6180486 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3944. Min Range: -7.3944
Max Act: 6.8632. Min Act: -0.1700
Data Index: 5073401 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3944. Min Range: -7.3944
Max Act: 6.8632. Min Act: -0.1700
Data Index: 8609296 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3944. Min Range: -7.3944
Max Act: 6.8632. Min Act: -0.1700
Data Index: 1119903 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3944. Min Range: -7.3944
Max Act: 6.8319. Min Act: -0.1700
Data Index: 412117 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3944. Min Range: -7.3944
Max Act: 6.8007. Min Act: -0.1700
Data Index: 5743103 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3944. Min Range: -7.3944
Max Act: 6.8007. Min Act: -0.1700
Data Index: 8723175 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19