Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3601 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7235. Min Range: -8.7235
Max Act: 8.7235. Min Act: -0.1700
Data Index: 3239337 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7235. Min Range: -8.7235
Max Act: 8.3485. Min Act: -0.1700
Data Index: 4824344 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7235. Min Range: -8.7235
Max Act: 8.3485. Min Act: -0.1700
Data Index: 4890486 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7235. Min Range: -8.7235
Max Act: 8.3485. Min Act: -0.1700
Data Index: 2353626 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7235. Min Range: -8.7235
Max Act: 8.2860. Min Act: -0.1700
Data Index: 2556848 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7235. Min Range: -8.7235
Max Act: 8.1297. Min Act: -0.1700
Data Index: 3798242 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7235. Min Range: -8.7235
Max Act: 8.2235. Min Act: -0.1700
Data Index: 1145163 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7235. Min Range: -8.7235
Max Act: 8.1297. Min Act: -0.1700
Data Index: 5571935 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7235. Min Range: -8.7235
Max Act: 8.1297. Min Act: -0.1700
Data Index: 7988545 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7235. Min Range: -8.7235
Max Act: 8.1297. Min Act: -0.1700
Data Index: 6530906 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7235. Min Range: -8.7235
Max Act: 8.0672. Min Act: -0.1700
Data Index: 8553790 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7235. Min Range: -8.7235
Max Act: 8.0360. Min Act: -0.1700
Data Index: 343995 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7235. Min Range: -8.7235
Max Act: 8.0047. Min Act: -0.1700
Data Index: 2821607 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7235. Min Range: -8.7235
Max Act: 7.9735. Min Act: -0.1700
Data Index: 8612507 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7235. Min Range: -8.7235
Max Act: 7.9735. Min Act: -0.1700
Data Index: 3469172 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7235. Min Range: -8.7235
Max Act: 7.9735. Min Act: -0.1700
Data Index: 2023868 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7235. Min Range: -8.7235
Max Act: 7.9735. Min Act: -0.1700
Data Index: 2112998 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7235. Min Range: -8.7235
Max Act: 7.9110. Min Act: -0.1700
Data Index: 4168607 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7235. Min Range: -8.7235
Max Act: 7.9422. Min Act: -0.1700
Data Index: 2236668 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7235. Min Range: -8.7235
Max Act: 7.8797. Min Act: -0.1700
Data Index: 3320814 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19