Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2165 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.7739. Min Act: -0.1700
Data Index: 608587 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.7427. Min Act: -0.1700
Data Index: 7078088 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.6802. Min Act: -0.1700
Data Index: 3777651 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.6802. Min Act: -0.1700
Data Index: 5270988 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.6489. Min Act: -0.1700
Data Index: 8207255 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.6489. Min Act: -0.1700
Data Index: 3622107 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.6489. Min Act: -0.1700
Data Index: 5849954 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.6177. Min Act: -0.1700
Data Index: 6023660 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.6177. Min Act: -0.1700
Data Index: 3295836 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.6177. Min Act: -0.1700
Data Index: 869241 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.6177. Min Act: -0.1700
Data Index: 282579 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.6177. Min Act: -0.1700
Data Index: 6512865 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.5864. Min Act: -0.1700
Data Index: 2618766 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.5864. Min Act: -0.1700
Data Index: 2258866 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.5864. Min Act: -0.1700
Data Index: 248361 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.5864. Min Act: -0.1700
Data Index: 654277 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.5864. Min Act: -0.1700
Data Index: 2889956 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.5864. Min Act: -0.1700
Data Index: 1742784 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.5864. Min Act: -0.1700
Data Index: 2568519 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7739. Min Range: -4.7739
Max Act: 4.6177. Min Act: -0.1700
Data Index: 40617 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19