Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3143 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.7946. Min Act: -0.1700
Data Index: 6776893 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.7477. Min Act: -0.1700
Data Index: 5042120 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.6851. Min Act: -0.1700
Data Index: 3727597 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.6538. Min Act: -0.1700
Data Index: 6286232 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.6069. Min Act: -0.1700
Data Index: 7738015 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.5286. Min Act: -0.1700
Data Index: 6930556 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.4659. Min Act: -0.1700
Data Index: 7776089 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.4816. Min Act: -0.1700
Data Index: 1375334 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.4973. Min Act: -0.1700
Data Index: 6505669 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.4816. Min Act: -0.1700
Data Index: 8031877 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.4346. Min Act: -0.1700
Data Index: 7786749 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.4503. Min Act: -0.1700
Data Index: 4587929 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.4503. Min Act: -0.1700
Data Index: 1829977 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.4659. Min Act: -0.1700
Data Index: 2287856 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.4503. Min Act: -0.1700
Data Index: 8517817 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.4503. Min Act: -0.1700
Data Index: 3172734 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.4032. Min Act: -0.1700
Data Index: 3007179 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.4032. Min Act: -0.1700
Data Index: 7613817 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.3876. Min Act: -0.1700
Data Index: 8488331 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7946. Min Range: -3.7946
Max Act: 3.3876. Min Act: -0.1700
Data Index: 3349128 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19