Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1185 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.8077. Min Act: -0.1700
Data Index: 7523786 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.6202. Min Act: -0.1700
Data Index: 3476092 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.5264. Min Act: -0.1700
Data Index: 3441564 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.5577. Min Act: -0.1700
Data Index: 3703114 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.4952. Min Act: -0.1700
Data Index: 6030462 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.4327. Min Act: -0.1700
Data Index: 8506074 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.4014. Min Act: -0.1700
Data Index: 3256428 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.3702. Min Act: -0.1700
Data Index: 6819353 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.3389. Min Act: -0.1700
Data Index: 8264007 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.3077. Min Act: -0.1700
Data Index: 1549456 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.3702. Min Act: -0.1700
Data Index: 7717538 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.3077. Min Act: -0.1700
Data Index: 5818162 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.3077. Min Act: -0.1700
Data Index: 5621202 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.3077. Min Act: -0.1700
Data Index: 4978908 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.2764. Min Act: -0.1700
Data Index: 202775 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.2764. Min Act: -0.1700
Data Index: 2524649 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.2452. Min Act: -0.1700
Data Index: 1582510 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.2452. Min Act: -0.1700
Data Index: 6339385 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.2139. Min Act: -0.1700
Data Index: 6771542 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8077. Min Range: -7.8077
Max Act: 7.2139. Min Act: -0.1700
Data Index: 3159407 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19