Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5881 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.7103. Min Act: -0.1700
Data Index: 1536703 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.4603. Min Act: -0.1700
Data Index: 1669387 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.4603. Min Act: -0.1700
Data Index: 5533231 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.3978. Min Act: -0.1700
Data Index: 5078245 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.3665. Min Act: -0.1700
Data Index: 1519428 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.3353. Min Act: -0.1700
Data Index: 5580096 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.3353. Min Act: -0.1700
Data Index: 5580097 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.3040. Min Act: -0.1700
Data Index: 7576949 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.3040. Min Act: -0.1700
Data Index: 5580093 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.3040. Min Act: -0.1700
Data Index: 5728150 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.2103. Min Act: -0.1700
Data Index: 4868257 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.2415. Min Act: -0.1700
Data Index: 7601994 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.2415. Min Act: -0.1700
Data Index: 8697365 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.2415. Min Act: -0.1700
Data Index: 869169 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.2103. Min Act: -0.1700
Data Index: 357173 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.2415. Min Act: -0.1700
Data Index: 2771982 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.2103. Min Act: -0.1700
Data Index: 6487682 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.2103. Min Act: -0.1700
Data Index: 6993836 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.1478. Min Act: -0.1700
Data Index: 7615480 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7103. Min Range: -5.7103
Max Act: 5.1478. Min Act: -0.1700
Data Index: 7929097 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19