Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2562 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3150. Min Range: -7.3150
Max Act: 7.3150. Min Act: -0.1700
Data Index: 229359 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3150. Min Range: -7.3150
Max Act: 7.2212. Min Act: -0.1700
Data Index: 229369 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3150. Min Range: -7.3150
Max Act: 7.0650. Min Act: -0.1700
Data Index: 4812 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3150. Min Range: -7.3150
Max Act: 7.0025. Min Act: -0.1700
Data Index: 6717550 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3150. Min Range: -7.3150
Max Act: 6.8150. Min Act: -0.1700
Data Index: 5627574 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3150. Min Range: -7.3150
Max Act: 6.7525. Min Act: -0.1700
Data Index: 8097004 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3150. Min Range: -7.3150
Max Act: 6.6900. Min Act: -0.1700
Data Index: 1537927 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3150. Min Range: -7.3150
Max Act: 6.6587. Min Act: -0.1700
Data Index: 2847537 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3150. Min Range: -7.3150
Max Act: 6.6587. Min Act: -0.1700
Data Index: 626158 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3150. Min Range: -7.3150
Max Act: 6.5962. Min Act: -0.1700
Data Index: 3951431 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3150. Min Range: -7.3150
Max Act: 6.5962. Min Act: -0.1700
Data Index: 693627 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3150. Min Range: -7.3150
Max Act: 6.5650. Min Act: -0.1700
Data Index: 2924327 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3150. Min Range: -7.3150
Max Act: 6.5337. Min Act: -0.1700
Data Index: 3217646 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3150. Min Range: -7.3150
Max Act: 6.4712. Min Act: -0.1700
Data Index: 6337415 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3150. Min Range: -7.3150
Max Act: 6.4712. Min Act: -0.1700
Data Index: 3605000 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3150. Min Range: -7.3150
Max Act: 6.4712. Min Act: -0.1700
Data Index: 6563933 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3150. Min Range: -7.3150
Max Act: 6.4400. Min Act: -0.1700
Data Index: 1704931 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3150. Min Range: -7.3150
Max Act: 6.4087. Min Act: -0.1700
Data Index: 3233059 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3150. Min Range: -7.3150
Max Act: 6.3775. Min Act: -0.1700
Data Index: 863008 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3150. Min Range: -7.3150
Max Act: 6.3775. Min Act: -0.1700
Data Index: 8350744 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19