Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2924 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.2281. Min Act: -0.1700
Data Index: 4153988 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.2281. Min Act: -0.1700
Data Index: 5814303 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.1966. Min Act: -0.1700
Data Index: 7941284 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.1966. Min Act: -0.1700
Data Index: 3828428 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.1652. Min Act: -0.1700
Data Index: 5658661 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.1337. Min Act: -0.1700
Data Index: 5498048 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.1337. Min Act: -0.1700
Data Index: 6774214 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.1337. Min Act: -0.1700
Data Index: 8831100 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.1022. Min Act: -0.1700
Data Index: 3749968 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.1022. Min Act: -0.1700
Data Index: 1528939 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.1022. Min Act: -0.1700
Data Index: 8498707 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.0864. Min Act: -0.1700
Data Index: 5730529 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.0864. Min Act: -0.1700
Data Index: 6215640 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.0864. Min Act: -0.1700
Data Index: 7185368 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.0864. Min Act: -0.1700
Data Index: 2242101 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.0864. Min Act: -0.1700
Data Index: 561271 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.0706. Min Act: -0.1700
Data Index: 3156556 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.0706. Min Act: -0.1700
Data Index: 5974308 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.0706. Min Act: -0.1700
Data Index: 1019511 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2281. Min Range: -3.2281
Max Act: 3.0706. Min Act: -0.1700
Data Index: 1867241 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19