Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2604 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.4289. Min Act: -0.1700
Data Index: 7878692 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.3505. Min Act: -0.1700
Data Index: 2806737 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.3349. Min Act: -0.1700
Data Index: 6178002 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.3035. Min Act: -0.1700
Data Index: 6864049 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.2564. Min Act: -0.1700
Data Index: 2309459 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.2564. Min Act: -0.1700
Data Index: 8690698 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.2564. Min Act: -0.1700
Data Index: 4764950 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.2406. Min Act: -0.1700
Data Index: 4764949 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.2406. Min Act: -0.1700
Data Index: 8617686 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.2406. Min Act: -0.1700
Data Index: 2478052 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.2249. Min Act: -0.1700
Data Index: 4830676 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.2249. Min Act: -0.1700
Data Index: 7048170 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.2249. Min Act: -0.1700
Data Index: 6440775 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.2092. Min Act: -0.1700
Data Index: 6709620 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.2092. Min Act: -0.1700
Data Index: 3370989 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.1935. Min Act: -0.1700
Data Index: 2245364 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.1778. Min Act: -0.1700
Data Index: 5194764 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.1620. Min Act: -0.1700
Data Index: 1008836 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.1778. Min Act: -0.1700
Data Index: 4206074 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4289. Min Range: -3.4289
Max Act: 3.1778. Min Act: -0.1700
Data Index: 4083186 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19