Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2558 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.8240. Min Act: -0.1700
Data Index: 7787332 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.8240. Min Act: -0.1700
Data Index: 5132504 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.8240. Min Act: -0.1700
Data Index: 6984125 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7927. Min Act: -0.1700
Data Index: 719220 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7927. Min Act: -0.1700
Data Index: 6772547 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7927. Min Act: -0.1700
Data Index: 3072192 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7927. Min Act: -0.1700
Data Index: 3138948 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7927. Min Act: -0.1700
Data Index: 4856722 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7615. Min Act: -0.1700
Data Index: 5183289 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7302. Min Act: -0.1700
Data Index: 2573124 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7615. Min Act: -0.1700
Data Index: 1214696 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7615. Min Act: -0.1700
Data Index: 1214697 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7615. Min Act: -0.1700
Data Index: 1183938 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7302. Min Act: -0.1700
Data Index: 1127314 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7615. Min Act: -0.1700
Data Index: 3689575 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7615. Min Act: -0.1700
Data Index: 3401691 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7302. Min Act: -0.1700
Data Index: 7105897 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7302. Min Act: -0.1700
Data Index: 4880296 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7302. Min Act: -0.1700
Data Index: 132219 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8240. Min Range: -4.8240
Max Act: 4.7302. Min Act: -0.1700
Data Index: 5079784 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19