Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1858 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.5443. Min Act: -0.1700
Data Index: 7505382 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.5443. Min Act: -0.1700
Data Index: 540675 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.5130. Min Act: -0.1700
Data Index: 1518568 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.4505. Min Act: -0.1700
Data Index: 5045746 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.4193. Min Act: -0.1700
Data Index: 1753217 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.3880. Min Act: -0.1700
Data Index: 2468797 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.3568. Min Act: -0.1700
Data Index: 5761854 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.3568. Min Act: -0.1700
Data Index: 8482344 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.2943. Min Act: -0.1700
Data Index: 7013967 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.2630. Min Act: -0.1700
Data Index: 81775 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.2630. Min Act: -0.1700
Data Index: 2915881 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.2318. Min Act: -0.1700
Data Index: 7194675 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.2318. Min Act: -0.1700
Data Index: 4051810 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.2630. Min Act: -0.1700
Data Index: 5933491 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.2005. Min Act: -0.1700
Data Index: 4248553 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.2318. Min Act: -0.1700
Data Index: 3385255 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.2005. Min Act: -0.1700
Data Index: 6050785 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.2318. Min Act: -0.1700
Data Index: 2929344 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.2005. Min Act: -0.1700
Data Index: 6762269 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5443. Min Range: -5.5443
Max Act: 5.2005. Min Act: -0.1700
Data Index: 3707184 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19