Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3192. Min Range: -10.3192
Max Act: 10.3192. Min Act: -0.1700
Data Index: 6188493 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3192. Min Range: -10.3192
Max Act: 10.0067. Min Act: -0.1700
Data Index: 2261043 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.9442. Min Act: -0.1700
Data Index: 8273411 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.8192. Min Act: -0.1700
Data Index: 561485 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.8192. Min Act: -0.1700
Data Index: 3464798 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.7567. Min Act: -0.1700
Data Index: 4998768 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.6942. Min Act: -0.1700
Data Index: 6095678 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.6942. Min Act: -0.1700
Data Index: 3308814 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.6317. Min Act: -0.1700
Data Index: 6467514 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.6317. Min Act: -0.1700
Data Index: 2614703 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.5692. Min Act: -0.1700
Data Index: 487820 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.5067. Min Act: -0.1700
Data Index: 3837631 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.4442. Min Act: -0.1700
Data Index: 2228559 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.4442. Min Act: -0.1700
Data Index: 4642981 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.3817. Min Act: -0.1700
Data Index: 1915571 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.3817. Min Act: -0.1700
Data Index: 7599915 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.3192. Min Act: -0.1700
Data Index: 5972511 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.3192. Min Act: -0.1700
Data Index: 548833 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.3192. Min Act: -0.1700
Data Index: 2877467 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3192. Min Range: -10.3192
Max Act: 9.3192. Min Act: -0.1700
Data Index: 4682531 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19