Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2235 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5163. Min Range: -6.5163
Max Act: 6.5163. Min Act: -0.1700
Data Index: 5007034 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5163. Min Range: -6.5163
Max Act: 6.3288. Min Act: -0.1700
Data Index: 6707407 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.9850. Min Act: -0.1700
Data Index: 7127254 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.9538. Min Act: -0.1700
Data Index: 8710936 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.8288. Min Act: -0.1700
Data Index: 4288815 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.7663. Min Act: -0.1700
Data Index: 5010757 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.7038. Min Act: -0.1700
Data Index: 4018291 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.7350. Min Act: -0.1700
Data Index: 474468 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.7038. Min Act: -0.1700
Data Index: 6081605 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.7350. Min Act: -0.1700
Data Index: 3958136 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.7038. Min Act: -0.1700
Data Index: 922939 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.7038. Min Act: -0.1700
Data Index: 7562188 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.7038. Min Act: -0.1700
Data Index: 8017550 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.6725. Min Act: -0.1700
Data Index: 7178762 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.6725. Min Act: -0.1700
Data Index: 5939926 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.7038. Min Act: -0.1700
Data Index: 2834778 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.6100. Min Act: -0.1700
Data Index: 285729 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.6100. Min Act: -0.1700
Data Index: 8451214 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.6100. Min Act: -0.1700
Data Index: 691711 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5163. Min Range: -6.5163
Max Act: 5.6100. Min Act: -0.1700
Data Index: 1862995 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19