Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3695 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.5136. Min Act: -0.1700
Data Index: 586541 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.5136. Min Act: -0.1700
Data Index: 401757 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.4824. Min Act: -0.1700
Data Index: 7290058 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.4511. Min Act: -0.1700
Data Index: 8608184 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.4511. Min Act: -0.1700
Data Index: 207295 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.4199. Min Act: -0.1700
Data Index: 4641897 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.4199. Min Act: -0.1700
Data Index: 7521558 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.4199. Min Act: -0.1700
Data Index: 4142802 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.3886. Min Act: -0.1700
Data Index: 5535391 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.3886. Min Act: -0.1700
Data Index: 3354644 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.3574. Min Act: -0.1700
Data Index: 6730783 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.3886. Min Act: -0.1700
Data Index: 3577543 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.3886. Min Act: -0.1700
Data Index: 2177176 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.3886. Min Act: -0.1700
Data Index: 252727 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.3886. Min Act: -0.1700
Data Index: 8362023 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.3886. Min Act: -0.1700
Data Index: 4703133 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.3261. Min Act: -0.1700
Data Index: 8799904 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.2949. Min Act: -0.1700
Data Index: 19202 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.2636. Min Act: -0.1700
Data Index: 5680853 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.2324. Min Act: -0.1700
Data Index: 1460709 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19