Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.8847. Min Act: -0.1700
Data Index: 7502095 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.8535. Min Act: -0.1700
Data Index: 4820237 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.8222. Min Act: -0.1700
Data Index: 5444554 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.8222. Min Act: -0.1700
Data Index: 7483713 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.8222. Min Act: -0.1700
Data Index: 6149308 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.7910. Min Act: -0.1700
Data Index: 6333730 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.7597. Min Act: -0.1700
Data Index: 3422816 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.7597. Min Act: -0.1700
Data Index: 5193621 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.7597. Min Act: -0.1700
Data Index: 2435786 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.6972. Min Act: -0.1700
Data Index: 6217205 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.7285. Min Act: -0.1700
Data Index: 8390261 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.7285. Min Act: -0.1700
Data Index: 4578106 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.6972. Min Act: -0.1700
Data Index: 47900 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.6660. Min Act: -0.1700
Data Index: 4346147 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.6660. Min Act: -0.1700
Data Index: 6053108 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.6660. Min Act: -0.1700
Data Index: 5288339 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.6347. Min Act: -0.1700
Data Index: 8008163 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.6347. Min Act: -0.1700
Data Index: 8324446 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.6347. Min Act: -0.1700
Data Index: 47441 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8847. Min Range: -4.8847
Max Act: 4.6035. Min Act: -0.1700
Data Index: 5289589 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19