Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4536 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6881. Min Range: -8.6881
Max Act: 8.6881. Min Act: -0.1700
Data Index: 7488644 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6881. Min Range: -8.6881
Max Act: 8.1881. Min Act: -0.1700
Data Index: 4220372 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6881. Min Range: -8.6881
Max Act: 8.0631. Min Act: -0.1700
Data Index: 1722383 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6881. Min Range: -8.6881
Max Act: 8.0006. Min Act: -0.1700
Data Index: 4464315 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6881. Min Range: -8.6881
Max Act: 7.9381. Min Act: -0.1700
Data Index: 2369516 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6881. Min Range: -8.6881
Max Act: 7.8131. Min Act: -0.1700
Data Index: 6355086 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6881. Min Range: -8.6881
Max Act: 7.8756. Min Act: -0.1700
Data Index: 6686444 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6881. Min Range: -8.6881
Max Act: 7.8131. Min Act: -0.1700
Data Index: 5290133 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6881. Min Range: -8.6881
Max Act: 7.8131. Min Act: -0.1700
Data Index: 3137943 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6881. Min Range: -8.6881
Max Act: 7.8131. Min Act: -0.1700
Data Index: 3647431 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6881. Min Range: -8.6881
Max Act: 7.8131. Min Act: -0.1700
Data Index: 2255890 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6881. Min Range: -8.6881
Max Act: 7.7506. Min Act: -0.1700
Data Index: 4602716 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6881. Min Range: -8.6881
Max Act: 7.6881. Min Act: -0.1700
Data Index: 8195824 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6881. Min Range: -8.6881
Max Act: 7.7506. Min Act: -0.1700
Data Index: 5450870 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6881. Min Range: -8.6881
Max Act: 7.7506. Min Act: -0.1700
Data Index: 939011 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6881. Min Range: -8.6881
Max Act: 7.6256. Min Act: -0.1700
Data Index: 3038711 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6881. Min Range: -8.6881
Max Act: 7.6881. Min Act: -0.1700
Data Index: 6983968 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6881. Min Range: -8.6881
Max Act: 7.6881. Min Act: -0.1700
Data Index: 5967782 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6881. Min Range: -8.6881
Max Act: 7.6881. Min Act: -0.1700
Data Index: 4542732 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6881. Min Range: -8.6881
Max Act: 7.6881. Min Act: -0.1700
Data Index: 8573464 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19