Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3773 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0456. Min Range: -5.0456
Max Act: 5.0456. Min Act: -0.1700
Data Index: 5931832 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.9206. Min Act: -0.1700
Data Index: 6862335 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.7956. Min Act: -0.1700
Data Index: 6059086 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.7956. Min Act: -0.1700
Data Index: 2484839 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.7331. Min Act: -0.1700
Data Index: 2714463 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.6706. Min Act: -0.1700
Data Index: 3021133 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.6394. Min Act: -0.1700
Data Index: 4120418 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.6394. Min Act: -0.1700
Data Index: 7710497 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.6081. Min Act: -0.1700
Data Index: 5105305 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.5769. Min Act: -0.1700
Data Index: 1489148 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.5769. Min Act: -0.1700
Data Index: 2975921 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.5769. Min Act: -0.1700
Data Index: 7111425 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.5456. Min Act: -0.1700
Data Index: 3947746 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.5456. Min Act: -0.1700
Data Index: 3745093 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.5144. Min Act: -0.1700
Data Index: 5657825 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.5144. Min Act: -0.1700
Data Index: 8168887 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.5144. Min Act: -0.1700
Data Index: 3532034 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.4831. Min Act: -0.1700
Data Index: 2126679 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.5144. Min Act: -0.1700
Data Index: 3560904 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0456. Min Range: -5.0456
Max Act: 4.5144. Min Act: -0.1700
Data Index: 5052675 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19