Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 160 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.7831. Min Act: -0.1700
Data Index: 5367131 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.7519. Min Act: -0.1700
Data Index: 2407133 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.7206. Min Act: -0.1700
Data Index: 1271690 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.6269. Min Act: -0.1700
Data Index: 1676371 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.5956. Min Act: -0.1700
Data Index: 6751318 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.5956. Min Act: -0.1700
Data Index: 5408966 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.5331. Min Act: -0.1700
Data Index: 1185549 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.5331. Min Act: -0.1700
Data Index: 3317085 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.5331. Min Act: -0.1700
Data Index: 7446751 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.5019. Min Act: -0.1700
Data Index: 4117298 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.5019. Min Act: -0.1700
Data Index: 7746903 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.5019. Min Act: -0.1700
Data Index: 2534471 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.5019. Min Act: -0.1700
Data Index: 8066858 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.5019. Min Act: -0.1700
Data Index: 6861298 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.5019. Min Act: -0.1700
Data Index: 3977135 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.4706. Min Act: -0.1700
Data Index: 2186470 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.4706. Min Act: -0.1700
Data Index: 7046845 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.4706. Min Act: -0.1700
Data Index: 4499099 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.4706. Min Act: -0.1700
Data Index: 3874187 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7831. Min Range: -4.7831
Max Act: 4.4394. Min Act: -0.1700
Data Index: 5593195 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19