Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3598 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.8714. Min Act: -0.1700
Data Index: 849538 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.7464. Min Act: -0.1700
Data Index: 1126450 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.7464. Min Act: -0.1700
Data Index: 4934611 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.7464. Min Act: -0.1700
Data Index: 849537 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.6839. Min Act: -0.1700
Data Index: 2958585 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.6214. Min Act: -0.1700
Data Index: 2938964 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.6214. Min Act: -0.1700
Data Index: 5856248 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.6214. Min Act: -0.1700
Data Index: 35294 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.6214. Min Act: -0.1700
Data Index: 5577307 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.5902. Min Act: -0.1700
Data Index: 2911009 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.5902. Min Act: -0.1700
Data Index: 4978579 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.5902. Min Act: -0.1700
Data Index: 4978584 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.5902. Min Act: -0.1700
Data Index: 4002176 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.5902. Min Act: -0.1700
Data Index: 8815655 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.5902. Min Act: -0.1700
Data Index: 2330737 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.5277. Min Act: -0.1700
Data Index: 3826242 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.5589. Min Act: -0.1700
Data Index: 2026243 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.5589. Min Act: -0.1700
Data Index: 2735719 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.5589. Min Act: -0.1700
Data Index: 1612680 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8714. Min Range: -6.8714
Max Act: 6.5589. Min Act: -0.1700
Data Index: 2330736 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19