Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3193 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2136. Min Range: -9.2136
Max Act: 9.2136. Min Act: -0.1700
Data Index: 1188961 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2136. Min Range: -9.2136
Max Act: 9.0261. Min Act: -0.1700
Data Index: 1392520 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.7761. Min Act: -0.1700
Data Index: 6783510 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.7761. Min Act: -0.1700
Data Index: 5801833 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.6511. Min Act: -0.1700
Data Index: 1582443 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.6511. Min Act: -0.1700
Data Index: 3274254 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.5886. Min Act: -0.1700
Data Index: 826675 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.5886. Min Act: -0.1700
Data Index: 6763501 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.5886. Min Act: -0.1700
Data Index: 6993722 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.5886. Min Act: -0.1700
Data Index: 6422017 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.5261. Min Act: -0.1700
Data Index: 3830536 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.5886. Min Act: -0.1700
Data Index: 7318435 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.5261. Min Act: -0.1700
Data Index: 8747744 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.5261. Min Act: -0.1700
Data Index: 7184597 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.4636. Min Act: -0.1700
Data Index: 1995105 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.4636. Min Act: -0.1700
Data Index: 3575424 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.5261. Min Act: -0.1700
Data Index: 1155844 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.3386. Min Act: -0.1700
Data Index: 5590311 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.4011. Min Act: -0.1700
Data Index: 3477133 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2136. Min Range: -9.2136
Max Act: 8.4011. Min Act: -0.1700
Data Index: 4531807 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19