Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1680 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.8593. Min Act: -0.1700
Data Index: 2004906 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.8280. Min Act: -0.1700
Data Index: 2555712 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.8123. Min Act: -0.1700
Data Index: 2289494 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.7811. Min Act: -0.1700
Data Index: 2004907 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.7498. Min Act: -0.1700
Data Index: 8450070 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.7498. Min Act: -0.1700
Data Index: 2004908 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.7185. Min Act: -0.1700
Data Index: 7115372 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.7029. Min Act: -0.1700
Data Index: 6124057 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.6872. Min Act: -0.1700
Data Index: 5031407 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.6716. Min Act: -0.1700
Data Index: 3712548 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.6559. Min Act: -0.1700
Data Index: 7962024 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.6559. Min Act: -0.1700
Data Index: 8220528 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.6559. Min Act: -0.1700
Data Index: 3277046 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.6559. Min Act: -0.1700
Data Index: 7770926 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.6403. Min Act: -0.1700
Data Index: 1460689 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.6246. Min Act: -0.1700
Data Index: 2876542 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.6090. Min Act: -0.1700
Data Index: 3277045 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.6090. Min Act: -0.1700
Data Index: 7204419 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.6090. Min Act: -0.1700
Data Index: 2452212 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8593. Min Range: -3.8593
Max Act: 3.5933. Min Act: -0.1700
Data Index: 527320 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19