Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3095 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.9820. Min Act: -0.1700
Data Index: 4371244 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.9195. Min Act: -0.1700
Data Index: 4031607 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.8882. Min Act: -0.1700
Data Index: 5540663 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.8570. Min Act: -0.1700
Data Index: 3220322 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.7945. Min Act: -0.1700
Data Index: 6627285 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.7945. Min Act: -0.1700
Data Index: 720181 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.7632. Min Act: -0.1700
Data Index: 8142637 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.7320. Min Act: -0.1700
Data Index: 1211942 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.7007. Min Act: -0.1700
Data Index: 7511135 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.6695. Min Act: -0.1700
Data Index: 3528841 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.6695. Min Act: -0.1700
Data Index: 706705 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.6695. Min Act: -0.1700
Data Index: 2589183 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.6382. Min Act: -0.1700
Data Index: 3850308 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.6070. Min Act: -0.1700
Data Index: 4806553 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.6382. Min Act: -0.1700
Data Index: 5337085 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.6070. Min Act: -0.1700
Data Index: 2242646 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.6070. Min Act: -0.1700
Data Index: 1198258 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.6070. Min Act: -0.1700
Data Index: 2404415 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.6070. Min Act: -0.1700
Data Index: 5238119 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9820. Min Range: -5.9820
Max Act: 5.6070. Min Act: -0.1700
Data Index: 5642467 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19