Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5360 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1030. Min Range: -5.1030
Max Act: 5.1030. Min Act: -0.1700
Data Index: 7857388 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.9155. Min Act: -0.1700
Data Index: 2635427 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.8842. Min Act: -0.1700
Data Index: 6502406 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.8530. Min Act: -0.1700
Data Index: 6661240 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.8530. Min Act: -0.1700
Data Index: 7873612 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.8217. Min Act: -0.1700
Data Index: 5284625 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.8217. Min Act: -0.1700
Data Index: 2389210 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.7905. Min Act: -0.1700
Data Index: 7154472 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.7592. Min Act: -0.1700
Data Index: 747940 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.7280. Min Act: -0.1700
Data Index: 1330161 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.6655. Min Act: -0.1700
Data Index: 1382218 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.6655. Min Act: -0.1700
Data Index: 2812832 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.6655. Min Act: -0.1700
Data Index: 203104 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.6342. Min Act: -0.1700
Data Index: 2677162 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.6342. Min Act: -0.1700
Data Index: 6159036 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.5717. Min Act: -0.1700
Data Index: 5307922 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.6030. Min Act: -0.1700
Data Index: 6246608 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.6030. Min Act: -0.1700
Data Index: 8440336 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.5717. Min Act: -0.1700
Data Index: 386227 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1030. Min Range: -5.1030
Max Act: 4.5717. Min Act: -0.1700
Data Index: 5282372 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19