Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3311 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.8565. Min Act: -0.1700
Data Index: 8272159 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.6690. Min Act: -0.1700
Data Index: 3544500 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.6065. Min Act: -0.1700
Data Index: 420213 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.5440. Min Act: -0.1700
Data Index: 1196443 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.4815. Min Act: -0.1700
Data Index: 3040515 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.5440. Min Act: -0.1700
Data Index: 5595660 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.4815. Min Act: -0.1700
Data Index: 3177798 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.4815. Min Act: -0.1700
Data Index: 6020941 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.4815. Min Act: -0.1700
Data Index: 8134054 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.5440. Min Act: -0.1700
Data Index: 7682192 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.4190. Min Act: -0.1700
Data Index: 1443974 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.3565. Min Act: -0.1700
Data Index: 7703704 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.3565. Min Act: -0.1700
Data Index: 8770927 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.3565. Min Act: -0.1700
Data Index: 2379384 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.2940. Min Act: -0.1700
Data Index: 4135702 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.2940. Min Act: -0.1700
Data Index: 2853285 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.2940. Min Act: -0.1700
Data Index: 759113 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.2940. Min Act: -0.1700
Data Index: 2931425 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.2940. Min Act: -0.1700
Data Index: 1357909 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8565. Min Range: -8.8565
Max Act: 8.2315. Min Act: -0.1700
Data Index: 7534746 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19