Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2545 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.8985. Min Act: -0.1700
Data Index: 1951845 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.7110. Min Act: -0.1700
Data Index: 444622 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.7735. Min Act: -0.1700
Data Index: 5224859 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.7110. Min Act: -0.1700
Data Index: 3312041 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.7110. Min Act: -0.1700
Data Index: 3915565 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.6485. Min Act: -0.1700
Data Index: 335574 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.6485. Min Act: -0.1700
Data Index: 1145551 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.6485. Min Act: -0.1700
Data Index: 7082793 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.5860. Min Act: -0.1700
Data Index: 2994612 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.5860. Min Act: -0.1700
Data Index: 8720102 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.5860. Min Act: -0.1700
Data Index: 7903093 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.5860. Min Act: -0.1700
Data Index: 416671 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.5860. Min Act: -0.1700
Data Index: 2049215 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.5860. Min Act: -0.1700
Data Index: 8782055 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.5235. Min Act: -0.1700
Data Index: 6889344 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.5235. Min Act: -0.1700
Data Index: 5981034 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.5235. Min Act: -0.1700
Data Index: 5635734 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.5235. Min Act: -0.1700
Data Index: 2813619 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.5235. Min Act: -0.1700
Data Index: 1685065 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8985. Min Range: -7.8985
Max Act: 7.5235. Min Act: -0.1700
Data Index: 8054518 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19