Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3314 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8676. Min Range: -9.8676
Max Act: 9.8676. Min Act: -0.1700
Data Index: 7926142 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.8676. Min Act: -0.1698
Data Index: 8478536 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.7426. Min Act: -0.1700
Data Index: 6135484 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.5239. Min Act: -0.1700
Data Index: 7214515 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.5239. Min Act: -0.1700
Data Index: 7485167 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.4926. Min Act: -0.1700
Data Index: 661057 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.3676. Min Act: -0.1700
Data Index: 2916719 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.3676. Min Act: -0.1700
Data Index: 4556841 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.3676. Min Act: -0.1697
Data Index: 7547734 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.3364. Min Act: -0.1700
Data Index: 6898482 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.3051. Min Act: -0.1700
Data Index: 2916714 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.2739. Min Act: -0.1700
Data Index: 3893751 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.2114. Min Act: -0.1700
Data Index: 7010 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.2114. Min Act: -0.1700
Data Index: 3229129 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.2114. Min Act: -0.1700
Data Index: 7537172 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.2114. Min Act: -0.1700
Data Index: 864186 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.2114. Min Act: -0.1700
Data Index: 6175503 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8676. Min Range: -9.8676
Max Act: 8.0864. Min Act: -0.1700
Data Index: 6774048 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8676. Min Range: -9.8676
Max Act: 7.9614. Min Act: -0.1699
Data Index: 8386556 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8676. Min Range: -9.8676
Max Act: 7.8676. Min Act: -0.1700
Data Index: 2916716 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19