Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3368 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4585. Min Range: -10.4585
Max Act: 10.4585. Min Act: -0.1700
Data Index: 2179571 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4585. Min Range: -10.4585
Max Act: 10.1460. Min Act: -0.1700
Data Index: 8295676 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.9585. Min Act: -0.1700
Data Index: 8718167 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4585. Min Range: -10.4585
Max Act: 10.0210. Min Act: -0.1700
Data Index: 6067727 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.8960. Min Act: -0.1700
Data Index: 8304982 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.8335. Min Act: -0.1700
Data Index: 3482831 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.8960. Min Act: -0.1700
Data Index: 2110132 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.8960. Min Act: -0.1700
Data Index: 2159483 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.7710. Min Act: -0.1700
Data Index: 490565 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.7710. Min Act: -0.1700
Data Index: 1436006 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.6460. Min Act: -0.1700
Data Index: 303142 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.6460. Min Act: -0.1700
Data Index: 5871593 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.6460. Min Act: -0.1700
Data Index: 5778585 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.6460. Min Act: -0.1700
Data Index: 1764608 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.6460. Min Act: -0.1700
Data Index: 1743316 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.6460. Min Act: -0.1700
Data Index: 5341634 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.6460. Min Act: -0.1700
Data Index: 5960157 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.5210. Min Act: -0.1700
Data Index: 8322638 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.5835. Min Act: -0.1700
Data Index: 5493515 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4585. Min Range: -10.4585
Max Act: 9.5835. Min Act: -0.1700
Data Index: 4969679 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19