Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6025 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0059. Min Range: -7.0059
Max Act: 7.0059. Min Act: -0.1700
Data Index: 6194957 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0059. Min Range: -7.0059
Max Act: 7.0059. Min Act: -0.1700
Data Index: 1093037 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.8809. Min Act: -0.1700
Data Index: 2583727 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.8496. Min Act: -0.1700
Data Index: 8477223 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.8184. Min Act: -0.1700
Data Index: 3068620 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.7871. Min Act: -0.1700
Data Index: 5165488 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.7559. Min Act: -0.1700
Data Index: 7089485 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.7871. Min Act: -0.1700
Data Index: 3935527 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.7559. Min Act: -0.1700
Data Index: 3441695 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.6934. Min Act: -0.1700
Data Index: 6760012 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.6934. Min Act: -0.1700
Data Index: 1755065 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.6934. Min Act: -0.1700
Data Index: 8580346 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.6621. Min Act: -0.1700
Data Index: 4575374 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.6309. Min Act: -0.1700
Data Index: 5620674 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.6621. Min Act: -0.1700
Data Index: 5173066 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.5996. Min Act: -0.1700
Data Index: 8321391 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.5996. Min Act: -0.1700
Data Index: 613259 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.5684. Min Act: -0.1700
Data Index: 5328307 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.5996. Min Act: -0.1700
Data Index: 325017 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0059. Min Range: -7.0059
Max Act: 6.5371. Min Act: -0.1700
Data Index: 7837127 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19