Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2579 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.6585. Min Act: -0.1700
Data Index: 8547909 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.5960. Min Act: -0.1700
Data Index: 1519544 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.5647. Min Act: -0.1700
Data Index: 8435499 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.3772. Min Act: -0.1700
Data Index: 3251809 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.3460. Min Act: -0.1700
Data Index: 1086002 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.3772. Min Act: -0.1700
Data Index: 6352846 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.3147. Min Act: -0.1700
Data Index: 3199213 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.3147. Min Act: -0.1700
Data Index: 3251810 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.2835. Min Act: -0.1700
Data Index: 1662972 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.2522. Min Act: -0.1700
Data Index: 4770470 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.2522. Min Act: -0.1700
Data Index: 4289475 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.2210. Min Act: -0.1700
Data Index: 7589069 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.2210. Min Act: -0.1700
Data Index: 1702644 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.2210. Min Act: -0.1700
Data Index: 6109043 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.1897. Min Act: -0.1700
Data Index: 253813 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.1585. Min Act: -0.1700
Data Index: 2858468 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.1897. Min Act: -0.1700
Data Index: 6980460 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.1897. Min Act: -0.1700
Data Index: 8009162 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.1897. Min Act: -0.1700
Data Index: 618364 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6585. Min Range: -5.6585
Max Act: 5.1897. Min Act: -0.1700
Data Index: 4770468 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19