Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2606 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.6086. Min Act: -0.1700
Data Index: 6954857 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.5148. Min Act: -0.1700
Data Index: 6351738 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.4211. Min Act: -0.1700
Data Index: 1684948 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.4211. Min Act: -0.1700
Data Index: 4457024 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.3586. Min Act: -0.1700
Data Index: 1015523 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.3273. Min Act: -0.1700
Data Index: 6705008 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.3273. Min Act: -0.1700
Data Index: 898072 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.3273. Min Act: -0.1700
Data Index: 5263537 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.2961. Min Act: -0.1700
Data Index: 890733 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.2961. Min Act: -0.1700
Data Index: 7139243 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.2961. Min Act: -0.1700
Data Index: 5519243 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.2961. Min Act: -0.1700
Data Index: 4106767 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.2961. Min Act: -0.1700
Data Index: 1312350 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.2648. Min Act: -0.1700
Data Index: 2338772 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.2648. Min Act: -0.1700
Data Index: 4707084 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.2648. Min Act: -0.1700
Data Index: 213332 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.2648. Min Act: -0.1700
Data Index: 8646863 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.2648. Min Act: -0.1700
Data Index: 1375917 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.2336. Min Act: -0.1700
Data Index: 5642229 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6086. Min Range: -4.6086
Max Act: 4.2648. Min Act: -0.1700
Data Index: 5651872 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19