Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 982 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.9402. Min Act: -0.1700
Data Index: 677310 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.9402. Min Act: -0.1700
Data Index: 1061393 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.5339. Min Act: -0.1700
Data Index: 6369990 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.5027. Min Act: -0.1700
Data Index: 6522795 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.3777. Min Act: -0.1700
Data Index: 2613559 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.3777. Min Act: -0.1700
Data Index: 2613565 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.3777. Min Act: -0.1700
Data Index: 2613570 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.3464. Min Act: -0.1700
Data Index: 6569909 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.3464. Min Act: -0.1700
Data Index: 2613572 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.3464. Min Act: -0.1700
Data Index: 7081041 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.3152. Min Act: -0.1700
Data Index: 2613561 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.3152. Min Act: -0.1700
Data Index: 2613563 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.2839. Min Act: -0.1700
Data Index: 5053266 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.2839. Min Act: -0.1700
Data Index: 7170163 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.3152. Min Act: -0.1700
Data Index: 4189220 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.2527. Min Act: -0.1700
Data Index: 2613568 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.2839. Min Act: -0.1700
Data Index: 4396019 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.2214. Min Act: -0.1700
Data Index: 3142421 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.2214. Min Act: -0.1700
Data Index: 4189221 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9402. Min Range: -5.9402
Max Act: 5.2214. Min Act: -0.1700
Data Index: 2151998 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19