Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2811 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1708. Min Range: -8.1708
Max Act: 8.1708. Min Act: -0.1700
Data Index: 1956018 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.9833. Min Act: -0.1700
Data Index: 3901519 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.7645. Min Act: -0.1700
Data Index: 5642120 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.6708. Min Act: -0.1700
Data Index: 8637890 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.7333. Min Act: -0.1700
Data Index: 3818562 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.6708. Min Act: -0.1700
Data Index: 3342867 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.6395. Min Act: -0.1700
Data Index: 7853729 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.6395. Min Act: -0.1700
Data Index: 3896999 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.6395. Min Act: -0.1700
Data Index: 1962780 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.6083. Min Act: -0.1700
Data Index: 2393935 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.6708. Min Act: -0.1700
Data Index: 4923128 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.6083. Min Act: -0.1700
Data Index: 4384866 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.5770. Min Act: -0.1700
Data Index: 4674612 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.5770. Min Act: -0.1700
Data Index: 2411540 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.5770. Min Act: -0.1700
Data Index: 477655 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.4833. Min Act: -0.1700
Data Index: 6225598 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.5145. Min Act: -0.1700
Data Index: 3456313 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.4833. Min Act: -0.1700
Data Index: 5811104 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.5145. Min Act: -0.1700
Data Index: 4660492 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1708. Min Range: -8.1708
Max Act: 7.5145. Min Act: -0.1700
Data Index: 5839009 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19