Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.8647. Min Act: -0.1700
Data Index: 2867060 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.6147. Min Act: -0.1700
Data Index: 2087246 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.5835. Min Act: -0.1700
Data Index: 7086328 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.5835. Min Act: -0.1700
Data Index: 6238050 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.5522. Min Act: -0.1700
Data Index: 1100367 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.5210. Min Act: -0.1700
Data Index: 3900273 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.4897. Min Act: -0.1700
Data Index: 5581602 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.4897. Min Act: -0.1700
Data Index: 7108208 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.4897. Min Act: -0.1700
Data Index: 7757769 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.4897. Min Act: -0.1700
Data Index: 627410 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.4585. Min Act: -0.1700
Data Index: 1609832 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.4585. Min Act: -0.1700
Data Index: 2079386 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.4585. Min Act: -0.1700
Data Index: 3799653 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.4585. Min Act: -0.1700
Data Index: 7644802 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.4272. Min Act: -0.1700
Data Index: 560960 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.4585. Min Act: -0.1700
Data Index: 6713439 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.4272. Min Act: -0.1700
Data Index: 866117 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.4272. Min Act: -0.1700
Data Index: 2610481 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.4272. Min Act: -0.1700
Data Index: 2417334 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8647. Min Range: -5.8647
Max Act: 5.4272. Min Act: -0.1700
Data Index: 3189990 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19