Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2571 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.5203. Min Act: -0.1700
Data Index: 5812887 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.3015. Min Act: -0.1700
Data Index: 1760938 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.2703. Min Act: -0.1700
Data Index: 7703057 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.2078. Min Act: -0.1700
Data Index: 3259103 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.2703. Min Act: -0.1700
Data Index: 3981182 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.1453. Min Act: -0.1700
Data Index: 6839022 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.1140. Min Act: -0.1700
Data Index: 3314533 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.0828. Min Act: -0.1700
Data Index: 598021 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.0515. Min Act: -0.1700
Data Index: 5236664 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.0515. Min Act: -0.1700
Data Index: 3271903 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.0515. Min Act: -0.1700
Data Index: 4020779 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.0203. Min Act: -0.1700
Data Index: 4665729 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5203. Min Range: -6.5203
Max Act: 6.0203. Min Act: -0.1700
Data Index: 3981177 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5203. Min Range: -6.5203
Max Act: 5.9890. Min Act: -0.1700
Data Index: 1684292 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5203. Min Range: -6.5203
Max Act: 5.9578. Min Act: -0.1700
Data Index: 3981178 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5203. Min Range: -6.5203
Max Act: 5.9578. Min Act: -0.1700
Data Index: 3981179 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5203. Min Range: -6.5203
Max Act: 5.9578. Min Act: -0.1700
Data Index: 6839024 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5203. Min Range: -6.5203
Max Act: 5.9265. Min Act: -0.1700
Data Index: 7757928 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5203. Min Range: -6.5203
Max Act: 5.9265. Min Act: -0.1700
Data Index: 594482 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5203. Min Range: -6.5203
Max Act: 5.9265. Min Act: -0.1700
Data Index: 2504037 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19