Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3721 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.8163. Min Act: -0.1700
Data Index: 7037739 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.7844. Min Act: -0.1700
Data Index: 2640124 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.7046. Min Act: -0.1699
Data Index: 4337051 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.7366. Min Act: -0.1700
Data Index: 7037737 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.6886. Min Act: -0.1700
Data Index: 2913377 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.6886. Min Act: -0.1700
Data Index: 1254444 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.6244. Min Act: -0.1700
Data Index: 6281445 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.6083. Min Act: -0.1700
Data Index: 6659933 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.6244. Min Act: -0.1700
Data Index: 610083 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5761. Min Act: -0.1700
Data Index: 2147301 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5600. Min Act: -0.1700
Data Index: 1988543 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5600. Min Act: -0.1700
Data Index: 171789 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5439. Min Act: -0.1697
Data Index: 5937624 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5761. Min Act: -0.1698
Data Index: 1793844 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5439. Min Act: -0.1700
Data Index: 880797 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5277. Min Act: -0.1698
Data Index: 2783671 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5277. Min Act: -0.1700
Data Index: 7037738 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5115. Min Act: -0.1700
Data Index: 649603 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5115. Min Act: -0.1700
Data Index: 1562047 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5115. Min Act: -0.1699
Data Index: 2640118 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19