Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3346 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.6287. Min Act: -0.1700
Data Index: 7020660 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.5974. Min Act: -0.1700
Data Index: 6019345 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.5349. Min Act: -0.1700
Data Index: 699855 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.5349. Min Act: -0.1700
Data Index: 3248327 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.4724. Min Act: -0.1700
Data Index: 8758397 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.4724. Min Act: -0.1700
Data Index: 7191615 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.4412. Min Act: -0.1700
Data Index: 4355368 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.4099. Min Act: -0.1700
Data Index: 542207 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.4099. Min Act: -0.1700
Data Index: 5582264 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.4099. Min Act: -0.1700
Data Index: 70836 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.3787. Min Act: -0.1700
Data Index: 5222473 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.3787. Min Act: -0.1700
Data Index: 7210637 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.3474. Min Act: -0.1700
Data Index: 7751541 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.3787. Min Act: -0.1700
Data Index: 448023 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.3162. Min Act: -0.1700
Data Index: 5426610 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.3474. Min Act: -0.1700
Data Index: 8471695 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.3162. Min Act: -0.1700
Data Index: 2128060 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.3162. Min Act: -0.1700
Data Index: 288652 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.2537. Min Act: -0.1700
Data Index: 1214403 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6287. Min Range: -7.6287
Max Act: 7.2537. Min Act: -0.1700
Data Index: 4075889 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19