Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1612 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1291. Min Range: -7.1291
Max Act: 7.1291. Min Act: -0.1700
Data Index: 2222321 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1291. Min Range: -7.1291
Max Act: 7.0666. Min Act: -0.1700
Data Index: 5268161 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.9728. Min Act: -0.1700
Data Index: 2254503 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.8166. Min Act: -0.1700
Data Index: 2920424 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.7853. Min Act: -0.1700
Data Index: 1278242 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.7853. Min Act: -0.1700
Data Index: 1891956 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.7541. Min Act: -0.1700
Data Index: 1910557 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.6916. Min Act: -0.1700
Data Index: 4725741 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.6916. Min Act: -0.1700
Data Index: 1235669 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.6291. Min Act: -0.1700
Data Index: 6350085 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.6291. Min Act: -0.1700
Data Index: 2599423 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.6291. Min Act: -0.1700
Data Index: 5704585 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.5666. Min Act: -0.1700
Data Index: 7737809 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.5041. Min Act: -0.1700
Data Index: 3163611 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.5353. Min Act: -0.1700
Data Index: 1791011 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.5041. Min Act: -0.1700
Data Index: 5343647 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.5353. Min Act: -0.1700
Data Index: 5959714 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.5353. Min Act: -0.1700
Data Index: 4382870 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.5353. Min Act: -0.1700
Data Index: 2501874 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1291. Min Range: -7.1291
Max Act: 6.5353. Min Act: -0.1700
Data Index: 5113357 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19