Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5236 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.4459. Min Act: -0.1700
Data Index: 5417633 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.4459. Min Act: -0.1700
Data Index: 7860231 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.4459. Min Act: -0.1700
Data Index: 1973357 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.2897. Min Act: -0.1700
Data Index: 7540307 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.2897. Min Act: -0.1700
Data Index: 4767387 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.2584. Min Act: -0.1700
Data Index: 69396 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.3209. Min Act: -0.1700
Data Index: 1283960 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.2897. Min Act: -0.1700
Data Index: 808884 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.2584. Min Act: -0.1700
Data Index: 4030429 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.2584. Min Act: -0.1700
Data Index: 1174105 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.2272. Min Act: -0.1700
Data Index: 3521145 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.2272. Min Act: -0.1700
Data Index: 6580556 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.1959. Min Act: -0.1700
Data Index: 2059125 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.1647. Min Act: -0.1700
Data Index: 1154384 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.1647. Min Act: -0.1700
Data Index: 8140613 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.1959. Min Act: -0.1700
Data Index: 5790377 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.1022. Min Act: -0.1700
Data Index: 4257732 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.1022. Min Act: -0.1700
Data Index: 2324000 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.1022. Min Act: -0.1700
Data Index: 5025673 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4459. Min Range: -6.4459
Max Act: 6.0709. Min Act: -0.1700
Data Index: 2854471 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19