Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1590 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6713. Min Range: -7.6713
Max Act: 7.6713. Min Act: -0.1700
Data Index: 6923856 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6713. Min Range: -7.6713
Max Act: 7.5151. Min Act: -0.1700
Data Index: 8231494 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6713. Min Range: -7.6713
Max Act: 7.3901. Min Act: -0.1700
Data Index: 3338391 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6713. Min Range: -7.6713
Max Act: 7.3276. Min Act: -0.1700
Data Index: 3353148 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6713. Min Range: -7.6713
Max Act: 7.2963. Min Act: -0.1700
Data Index: 2555329 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6713. Min Range: -7.6713
Max Act: 7.2026. Min Act: -0.1700
Data Index: 3369842 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6713. Min Range: -7.6713
Max Act: 7.2026. Min Act: -0.1700
Data Index: 8383565 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6713. Min Range: -7.6713
Max Act: 7.1713. Min Act: -0.1700
Data Index: 4829890 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6713. Min Range: -7.6713
Max Act: 7.1401. Min Act: -0.1700
Data Index: 6575625 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6713. Min Range: -7.6713
Max Act: 7.1401. Min Act: -0.1700
Data Index: 2517061 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6713. Min Range: -7.6713
Max Act: 7.1088. Min Act: -0.1700
Data Index: 1735911 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6713. Min Range: -7.6713
Max Act: 7.1088. Min Act: -0.1700
Data Index: 4344219 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6713. Min Range: -7.6713
Max Act: 7.1401. Min Act: -0.1700
Data Index: 5391695 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6713. Min Range: -7.6713
Max Act: 7.0776. Min Act: -0.1700
Data Index: 5321471 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6713. Min Range: -7.6713
Max Act: 7.0463. Min Act: -0.1700
Data Index: 8383574 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6713. Min Range: -7.6713
Max Act: 7.0151. Min Act: -0.1700
Data Index: 3640230 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6713. Min Range: -7.6713
Max Act: 6.9526. Min Act: -0.1700
Data Index: 7430203 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6713. Min Range: -7.6713
Max Act: 6.9526. Min Act: -0.1700
Data Index: 3166968 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6713. Min Range: -7.6713
Max Act: 6.9213. Min Act: -0.1700
Data Index: 5654744 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6713. Min Range: -7.6713
Max Act: 6.9213. Min Act: -0.1700
Data Index: 6579744 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19