Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3023 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0494. Min Range: -7.0494
Max Act: 7.0494. Min Act: -0.1700
Data Index: 1054632 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.6432. Min Act: -0.1700
Data Index: 8365430 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.6744. Min Act: -0.1700
Data Index: 5457949 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.5807. Min Act: -0.1700
Data Index: 2299671 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.4557. Min Act: -0.1700
Data Index: 1258329 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.4244. Min Act: -0.1700
Data Index: 3274405 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.3932. Min Act: -0.1700
Data Index: 43724 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.3307. Min Act: -0.1700
Data Index: 6423127 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.3307. Min Act: -0.1700
Data Index: 8298441 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.3307. Min Act: -0.1700
Data Index: 3347008 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.3307. Min Act: -0.1700
Data Index: 3721950 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.2994. Min Act: -0.1700
Data Index: 2037396 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.2994. Min Act: -0.1700
Data Index: 1121766 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.2682. Min Act: -0.1700
Data Index: 4478018 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.2682. Min Act: -0.1700
Data Index: 742920 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.2994. Min Act: -0.1700
Data Index: 5275909 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.2682. Min Act: -0.1700
Data Index: 6491929 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.2369. Min Act: -0.1700
Data Index: 6658947 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.2369. Min Act: -0.1700
Data Index: 958447 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0494. Min Range: -7.0494
Max Act: 6.2057. Min Act: -0.1700
Data Index: 6285149 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19