Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4698 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.5205. Min Act: -0.1700
Data Index: 2439197 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.4268. Min Act: -0.1700
Data Index: 7711664 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.4268. Min Act: -0.1700
Data Index: 6748585 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.3955. Min Act: -0.1700
Data Index: 6212876 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.3018. Min Act: -0.1700
Data Index: 918767 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.3018. Min Act: -0.1700
Data Index: 7049753 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.2705. Min Act: -0.1700
Data Index: 2324697 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.2705. Min Act: -0.1700
Data Index: 7049757 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.2080. Min Act: -0.1700
Data Index: 7049760 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.1143. Min Act: -0.1700
Data Index: 7049755 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.1143. Min Act: -0.1700
Data Index: 129143 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.0830. Min Act: -0.1700
Data Index: 6287409 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.0518. Min Act: -0.1700
Data Index: 4328164 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.0518. Min Act: -0.1700
Data Index: 7700585 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.0205. Min Act: -0.1700
Data Index: 1281195 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.0205. Min Act: -0.1700
Data Index: 5527031 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.0205. Min Act: -0.1700
Data Index: 2812602 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5205. Min Range: -7.5205
Max Act: 7.0205. Min Act: -0.1700
Data Index: 2439196 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5205. Min Range: -7.5205
Max Act: 6.9580. Min Act: -0.1700
Data Index: 2220325 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5205. Min Range: -7.5205
Max Act: 6.9268. Min Act: -0.1700
Data Index: 8439937 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19