Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2557 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5973. Min Act: -0.1700
Data Index: 3110290 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5973. Min Act: -0.1700
Data Index: 6207935 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5660. Min Act: -0.1700
Data Index: 8092920 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5660. Min Act: -0.1700
Data Index: 5147772 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5660. Min Act: -0.1700
Data Index: 273708 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5660. Min Act: -0.1700
Data Index: 3707056 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5347. Min Act: -0.1700
Data Index: 7073958 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5347. Min Act: -0.1700
Data Index: 3786539 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5347. Min Act: -0.1700
Data Index: 7492516 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5347. Min Act: -0.1700
Data Index: 7502172 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5347. Min Act: -0.1700
Data Index: 7896871 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5347. Min Act: -0.1700
Data Index: 4245020 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5347. Min Act: -0.1700
Data Index: 8140859 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5347. Min Act: -0.1700
Data Index: 8796685 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5347. Min Act: -0.1700
Data Index: 5036171 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5347. Min Act: -0.1700
Data Index: 2632618 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5033. Min Act: -0.1700
Data Index: 285389 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5033. Min Act: -0.1700
Data Index: 5114584 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5033. Min Act: -0.1700
Data Index: 2708222 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5973. Min Range: -3.5973
Max Act: 3.5033. Min Act: -0.1700
Data Index: 512285 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19