Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 502 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5288. Min Range: -7.5288
Max Act: 7.5288. Min Act: -0.1700
Data Index: 3963225 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5288. Min Range: -7.5288
Max Act: 7.3100. Min Act: -0.1700
Data Index: 986012 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.9350. Min Act: -0.1700
Data Index: 59970 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.9038. Min Act: -0.1700
Data Index: 7043112 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.9038. Min Act: -0.1700
Data Index: 1279510 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.8725. Min Act: -0.1700
Data Index: 3464702 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.8413. Min Act: -0.1700
Data Index: 6643229 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.7788. Min Act: -0.1700
Data Index: 62074 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.7788. Min Act: -0.1700
Data Index: 4277684 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.7163. Min Act: -0.1700
Data Index: 3801161 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.7475. Min Act: -0.1700
Data Index: 1205369 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.7163. Min Act: -0.1700
Data Index: 929826 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.7163. Min Act: -0.1700
Data Index: 8065810 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.7163. Min Act: -0.1700
Data Index: 3565707 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.6850. Min Act: -0.1700
Data Index: 4493397 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.6538. Min Act: -0.1700
Data Index: 2888003 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.6225. Min Act: -0.1700
Data Index: 6044910 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.6225. Min Act: -0.1700
Data Index: 4193766 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.5913. Min Act: -0.1700
Data Index: 2100105 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5288. Min Range: -7.5288
Max Act: 6.5600. Min Act: -0.1700
Data Index: 4380904 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19