Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2758 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.9284. Min Act: -0.1700
Data Index: 1105144 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.7722. Min Act: -0.1700
Data Index: 276906 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.7722. Min Act: -0.1700
Data Index: 296264 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.5847. Min Act: -0.1700
Data Index: 7966887 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.5534. Min Act: -0.1700
Data Index: 8421312 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.5534. Min Act: -0.1700
Data Index: 1634679 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.5222. Min Act: -0.1700
Data Index: 1912918 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.5222. Min Act: -0.1700
Data Index: 7498834 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.4909. Min Act: -0.1700
Data Index: 6320119 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.3972. Min Act: -0.1700
Data Index: 3883278 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.3972. Min Act: -0.1700
Data Index: 6704312 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.3972. Min Act: -0.1700
Data Index: 6895582 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.3972. Min Act: -0.1700
Data Index: 358707 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.3347. Min Act: -0.1700
Data Index: 3006176 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.3659. Min Act: -0.1700
Data Index: 8354991 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.3347. Min Act: -0.1700
Data Index: 1794644 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.3347. Min Act: -0.1700
Data Index: 7281832 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.3347. Min Act: -0.1700
Data Index: 4062644 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.3034. Min Act: -0.1700
Data Index: 7877935 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9284. Min Range: -6.9284
Max Act: 6.2722. Min Act: -0.1700
Data Index: 5042889 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19