Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4509 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.8225. Min Act: -0.1700
Data Index: 2192027 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.8537. Min Act: -0.1700
Data Index: 6648190 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.8225. Min Act: -0.1700
Data Index: 85882 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.7599. Min Act: -0.1700
Data Index: 1528923 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.6974. Min Act: -0.1700
Data Index: 2257091 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.7286. Min Act: -0.1700
Data Index: 6509026 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.6974. Min Act: -0.1700
Data Index: 4529804 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.6974. Min Act: -0.1700
Data Index: 2300984 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.6974. Min Act: -0.1700
Data Index: 686352 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.6661. Min Act: -0.1700
Data Index: 4346766 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.6974. Min Act: -0.1700
Data Index: 6598724 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.6661. Min Act: -0.1700
Data Index: 5340326 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.6661. Min Act: -0.1700
Data Index: 3388936 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.6661. Min Act: -0.1700
Data Index: 1417370 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.6661. Min Act: -0.1700
Data Index: 1941073 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.6661. Min Act: -0.1700
Data Index: 4296870 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.6661. Min Act: -0.1700
Data Index: 5096235 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.6191. Min Act: -0.1700
Data Index: 6321029 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.6348. Min Act: -0.1700
Data Index: 3328304 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8537. Min Range: -3.8537
Max Act: 3.6191. Min Act: -0.1700
Data Index: 6059321 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19