Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 995 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8188. Min Range: -7.8188
Max Act: 7.8188. Min Act: -0.1700
Data Index: 6892065 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8188. Min Range: -7.8188
Max Act: 7.4126. Min Act: -0.1700
Data Index: 4155823 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8188. Min Range: -7.8188
Max Act: 7.4126. Min Act: -0.1700
Data Index: 6625222 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8188. Min Range: -7.8188
Max Act: 7.3501. Min Act: -0.1700
Data Index: 6802489 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8188. Min Range: -7.8188
Max Act: 7.1313. Min Act: -0.1700
Data Index: 6486838 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8188. Min Range: -7.8188
Max Act: 7.1626. Min Act: -0.1700
Data Index: 8805337 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8188. Min Range: -7.8188
Max Act: 7.1626. Min Act: -0.1700
Data Index: 2502465 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8188. Min Range: -7.8188
Max Act: 7.1001. Min Act: -0.1700
Data Index: 2023573 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8188. Min Range: -7.8188
Max Act: 7.0688. Min Act: -0.1700
Data Index: 4303800 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8188. Min Range: -7.8188
Max Act: 7.0688. Min Act: -0.1700
Data Index: 8420997 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8188. Min Range: -7.8188
Max Act: 7.0063. Min Act: -0.1700
Data Index: 4558317 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8188. Min Range: -7.8188
Max Act: 7.0063. Min Act: -0.1700
Data Index: 4077768 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8188. Min Range: -7.8188
Max Act: 6.9751. Min Act: -0.1700
Data Index: 4225690 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8188. Min Range: -7.8188
Max Act: 7.0376. Min Act: -0.1700
Data Index: 1792191 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8188. Min Range: -7.8188
Max Act: 6.9438. Min Act: -0.1700
Data Index: 6207023 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8188. Min Range: -7.8188
Max Act: 6.9751. Min Act: -0.1700
Data Index: 2463759 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8188. Min Range: -7.8188
Max Act: 6.9751. Min Act: -0.1700
Data Index: 3867793 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8188. Min Range: -7.8188
Max Act: 6.9751. Min Act: -0.1700
Data Index: 7799381 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8188. Min Range: -7.8188
Max Act: 6.9751. Min Act: -0.1700
Data Index: 4523907 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8188. Min Range: -7.8188
Max Act: 6.9751. Min Act: -0.1700
Data Index: 3379012 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19