Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3660 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.8548. Min Act: -0.1700
Data Index: 7343126 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.5423. Min Act: -0.1700
Data Index: 195147 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.5735. Min Act: -0.1700
Data Index: 1173298 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.4485. Min Act: -0.1700
Data Index: 8802164 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.4173. Min Act: -0.1700
Data Index: 1300345 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.3548. Min Act: -0.1700
Data Index: 1136541 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.3548. Min Act: -0.1700
Data Index: 8064637 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.3235. Min Act: -0.1700
Data Index: 6229923 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.3235. Min Act: -0.1700
Data Index: 1786210 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.2923. Min Act: -0.1700
Data Index: 6925130 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.2298. Min Act: -0.1700
Data Index: 5190845 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.1985. Min Act: -0.1700
Data Index: 1981666 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.1985. Min Act: -0.1700
Data Index: 8513251 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.1985. Min Act: -0.1700
Data Index: 1213506 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.2298. Min Act: -0.1700
Data Index: 7473217 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.1673. Min Act: -0.1700
Data Index: 6618989 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.1985. Min Act: -0.1700
Data Index: 5167166 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.1360. Min Act: -0.1700
Data Index: 4979228 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.1360. Min Act: -0.1700
Data Index: 4319772 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8548. Min Range: -5.8548
Max Act: 5.1360. Min Act: -0.1700
Data Index: 5055199 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19