Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 451 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.3356. Min Act: -0.1700
Data Index: 2839128 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.3199. Min Act: -0.1700
Data Index: 508150 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2728. Min Act: -0.1700
Data Index: 2518871 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2728. Min Act: -0.1700
Data Index: 2940500 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2728. Min Act: -0.1700
Data Index: 495257 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2728. Min Act: -0.1700
Data Index: 2440051 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2571. Min Act: -0.1700
Data Index: 6302530 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2571. Min Act: -0.1700
Data Index: 5187883 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2414. Min Act: -0.1700
Data Index: 4880864 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2571. Min Act: -0.1700
Data Index: 6885817 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2571. Min Act: -0.1700
Data Index: 6333375 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2571. Min Act: -0.1700
Data Index: 3899106 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2414. Min Act: -0.1700
Data Index: 1212581 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2414. Min Act: -0.1700
Data Index: 4097778 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2414. Min Act: -0.1700
Data Index: 7956731 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2414. Min Act: -0.1700
Data Index: 7885107 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2414. Min Act: -0.1700
Data Index: 5367585 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2257. Min Act: -0.1700
Data Index: 6740252 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2257. Min Act: -0.1700
Data Index: 490581 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3356. Min Range: -3.3356
Max Act: 3.2257. Min Act: -0.1700
Data Index: 6042755 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19