Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.7932. Min Act: -0.1700
Data Index: 7657914 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.6682. Min Act: -0.1700
Data Index: 4938850 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.7307. Min Act: -0.1700
Data Index: 348953 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.7307. Min Act: -0.1700
Data Index: 7022385 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.4807. Min Act: -0.1700
Data Index: 4273347 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.4182. Min Act: -0.1700
Data Index: 7110808 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.4182. Min Act: -0.1700
Data Index: 6256297 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.3557. Min Act: -0.1700
Data Index: 5652676 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.3557. Min Act: -0.1700
Data Index: 8653183 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.2932. Min Act: -0.1700
Data Index: 5970474 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.2307. Min Act: -0.1700
Data Index: 276387 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.2307. Min Act: -0.1700
Data Index: 7257577 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.2307. Min Act: -0.1700
Data Index: 433069 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.2307. Min Act: -0.1700
Data Index: 8397823 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.2932. Min Act: -0.1700
Data Index: 575316 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.2307. Min Act: -0.1700
Data Index: 3931285 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.2307. Min Act: -0.1700
Data Index: 7452343 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.2307. Min Act: -0.1700
Data Index: 6989980 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.1682. Min Act: -0.1700
Data Index: 2347600 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7932. Min Range: -8.7932
Max Act: 8.1682. Min Act: -0.1700
Data Index: 3799733 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19