Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.4987. Min Act: -0.1700
Data Index: 3278518 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.3733. Min Act: -0.1700
Data Index: 2963849 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.3420. Min Act: -0.1700
Data Index: 2582286 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.3263. Min Act: -0.1700
Data Index: 4374712 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.3263. Min Act: -0.1700
Data Index: 7009151 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.3263. Min Act: -0.1700
Data Index: 352006 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.2792. Min Act: -0.1700
Data Index: 2171634 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.2949. Min Act: -0.1700
Data Index: 8283479 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.2792. Min Act: -0.1700
Data Index: 2840984 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.2635. Min Act: -0.1700
Data Index: 1085481 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.2478. Min Act: -0.1700
Data Index: 6399808 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.2320. Min Act: -0.1700
Data Index: 7081314 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.2163. Min Act: -0.1700
Data Index: 8558523 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.2320. Min Act: -0.1700
Data Index: 7675741 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.2478. Min Act: -0.1700
Data Index: 2488866 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.2320. Min Act: -0.1700
Data Index: 6351746 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.2163. Min Act: -0.1700
Data Index: 6866879 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.2163. Min Act: -0.1700
Data Index: 2632890 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.2163. Min Act: -0.1700
Data Index: 7454240 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4987. Min Range: -3.4987
Max Act: 3.2006. Min Act: -0.1700
Data Index: 802202 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19