Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5090 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0302. Min Range: -7.0302
Max Act: 7.0302. Min Act: -0.1700
Data Index: 1793129 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.9052. Min Act: -0.1700
Data Index: 7125656 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.9052. Min Act: -0.1700
Data Index: 2944934 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.8739. Min Act: -0.1700
Data Index: 3249402 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.8114. Min Act: -0.1700
Data Index: 1827874 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.7802. Min Act: -0.1700
Data Index: 5861574 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.7489. Min Act: -0.1700
Data Index: 4578881 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.7177. Min Act: -0.1700
Data Index: 2850412 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.7177. Min Act: -0.1700
Data Index: 4720082 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.6552. Min Act: -0.1700
Data Index: 5180248 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.6552. Min Act: -0.1700
Data Index: 7140178 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.6552. Min Act: -0.1700
Data Index: 7776127 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.6552. Min Act: -0.1700
Data Index: 2841562 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.6239. Min Act: -0.1700
Data Index: 5998225 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.6239. Min Act: -0.1700
Data Index: 3767574 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.6552. Min Act: -0.1700
Data Index: 2731134 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.5927. Min Act: -0.1700
Data Index: 5405292 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.5614. Min Act: -0.1700
Data Index: 4933377 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.5614. Min Act: -0.1700
Data Index: 3799181 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0302. Min Range: -7.0302
Max Act: 6.5927. Min Act: -0.1700
Data Index: 5125603 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19