Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2023 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5621. Min Range: -8.5621
Max Act: 8.5621. Min Act: -0.1700
Data Index: 7918599 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5621. Min Range: -8.5621
Max Act: 8.3121. Min Act: -0.1700
Data Index: 5267164 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5621. Min Range: -8.5621
Max Act: 8.1246. Min Act: -0.1700
Data Index: 909467 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5621. Min Range: -8.5621
Max Act: 8.1246. Min Act: -0.1700
Data Index: 8098306 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5621. Min Range: -8.5621
Max Act: 8.1246. Min Act: -0.1700
Data Index: 3829511 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5621. Min Range: -8.5621
Max Act: 8.0621. Min Act: -0.1700
Data Index: 4269110 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5621. Min Range: -8.5621
Max Act: 7.9683. Min Act: -0.1700
Data Index: 1462319 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5621. Min Range: -8.5621
Max Act: 7.9683. Min Act: -0.1700
Data Index: 4357833 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5621. Min Range: -8.5621
Max Act: 7.9371. Min Act: -0.1700
Data Index: 8113644 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5621. Min Range: -8.5621
Max Act: 7.9371. Min Act: -0.1700
Data Index: 6614864 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5621. Min Range: -8.5621
Max Act: 7.9058. Min Act: -0.1700
Data Index: 922427 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5621. Min Range: -8.5621
Max Act: 7.9058. Min Act: -0.1700
Data Index: 3094715 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5621. Min Range: -8.5621
Max Act: 7.8746. Min Act: -0.1700
Data Index: 1551394 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5621. Min Range: -8.5621
Max Act: 7.8746. Min Act: -0.1700
Data Index: 3618339 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5621. Min Range: -8.5621
Max Act: 7.8121. Min Act: -0.1700
Data Index: 217724 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5621. Min Range: -8.5621
Max Act: 7.8121. Min Act: -0.1700
Data Index: 3346066 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5621. Min Range: -8.5621
Max Act: 7.7808. Min Act: -0.1700
Data Index: 1724430 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5621. Min Range: -8.5621
Max Act: 7.7496. Min Act: -0.1700
Data Index: 7647003 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5621. Min Range: -8.5621
Max Act: 7.7496. Min Act: -0.1700
Data Index: 4389924 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5621. Min Range: -8.5621
Max Act: 7.7496. Min Act: -0.1700
Data Index: 3769308 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19