Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2138 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.5873. Min Act: -0.1700
Data Index: 8233638 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.5248. Min Act: -0.1700
Data Index: 7806414 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.4310. Min Act: -0.1700
Data Index: 6535596 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.3373. Min Act: -0.1700
Data Index: 6253350 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.3060. Min Act: -0.1700
Data Index: 8002331 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.2748. Min Act: -0.1700
Data Index: 6149530 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.2435. Min Act: -0.1700
Data Index: 4073177 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.2435. Min Act: -0.1700
Data Index: 1464717 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.2123. Min Act: -0.1700
Data Index: 2768491 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.2123. Min Act: -0.1700
Data Index: 6123874 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.2123. Min Act: -0.1700
Data Index: 456887 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.1185. Min Act: -0.1700
Data Index: 25161 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.1185. Min Act: -0.1700
Data Index: 33599 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.0873. Min Act: -0.1700
Data Index: 6028399 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.0873. Min Act: -0.1700
Data Index: 2029011 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.0873. Min Act: -0.1700
Data Index: 2538982 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.0873. Min Act: -0.1700
Data Index: 6980305 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.0873. Min Act: -0.1700
Data Index: 532624 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.0873. Min Act: -0.1700
Data Index: 3770207 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5873. Min Range: -6.5873
Max Act: 6.0560. Min Act: -0.1700
Data Index: 284215 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19