Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2851 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.5277. Min Act: -0.1700
Data Index: 4294819 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.3714. Min Act: -0.1700
Data Index: 6392256 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.3401. Min Act: -0.1700
Data Index: 3878734 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.3401. Min Act: -0.1700
Data Index: 6030669 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.3401. Min Act: -0.1700
Data Index: 572295 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.3089. Min Act: -0.1700
Data Index: 8116827 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.2776. Min Act: -0.1700
Data Index: 7291319 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.2464. Min Act: -0.1700
Data Index: 5891083 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.2464. Min Act: -0.1700
Data Index: 5587189 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.2464. Min Act: -0.1700
Data Index: 1677732 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.2464. Min Act: -0.1700
Data Index: 7191617 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.2464. Min Act: -0.1700
Data Index: 6809604 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.2151. Min Act: -0.1700
Data Index: 2302668 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.2464. Min Act: -0.1700
Data Index: 7831778 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.2151. Min Act: -0.1700
Data Index: 3003456 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.2151. Min Act: -0.1700
Data Index: 4685160 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.2151. Min Act: -0.1700
Data Index: 4411085 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.1839. Min Act: -0.1700
Data Index: 2114188 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.1526. Min Act: -0.1700
Data Index: 7446639 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5277. Min Range: -4.5277
Max Act: 4.1526. Min Act: -0.1700
Data Index: 5053341 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19