Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3807 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.9554. Min Act: -0.1700
Data Index: 2063980 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6741. Min Act: -0.1700
Data Index: 2186082 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4866. Min Act: -0.1700
Data Index: 416678 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4241. Min Act: -0.1700
Data Index: 4395110 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.3304. Min Act: -0.1700
Data Index: 4167687 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.3304. Min Act: -0.1700
Data Index: 1153026 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.2991. Min Act: -0.1700
Data Index: 4918494 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.2679. Min Act: -0.1700
Data Index: 1579688 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.2679. Min Act: -0.1700
Data Index: 8769182 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.2991. Min Act: -0.1700
Data Index: 504593 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.2054. Min Act: -0.1700
Data Index: 125545 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.2054. Min Act: -0.1700
Data Index: 8633106 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.2054. Min Act: -0.1700
Data Index: 785637 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.1429. Min Act: -0.1700
Data Index: 2725600 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.1116. Min Act: -0.1700
Data Index: 3628722 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.1116. Min Act: -0.1700
Data Index: 5367373 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.1429. Min Act: -0.1700
Data Index: 4024412 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.1429. Min Act: -0.1700
Data Index: 4685746 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.0491. Min Act: -0.1700
Data Index: 7866031 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.0804. Min Act: -0.1700
Data Index: 3705063 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19