Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3208 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.2824. Min Act: -0.1700
Data Index: 2258966 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.2824. Min Act: -0.1700
Data Index: 52237 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.2199. Min Act: -0.1700
Data Index: 3552075 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.2199. Min Act: -0.1700
Data Index: 8449169 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.1574. Min Act: -0.1700
Data Index: 3446433 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.1574. Min Act: -0.1700
Data Index: 5059150 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.1574. Min Act: -0.1700
Data Index: 1434097 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.1574. Min Act: -0.1700
Data Index: 7292351 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.0949. Min Act: -0.1700
Data Index: 8676969 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.0949. Min Act: -0.1700
Data Index: 2232741 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.0949. Min Act: -0.1700
Data Index: 6331319 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.0949. Min Act: -0.1700
Data Index: 2232724 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.0949. Min Act: -0.1700
Data Index: 5664350 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.0949. Min Act: -0.1700
Data Index: 1344786 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.0324. Min Act: -0.1700
Data Index: 8431644 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.0324. Min Act: -0.1700
Data Index: 1021233 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.0949. Min Act: -0.1700
Data Index: 5995876 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.0324. Min Act: -0.1700
Data Index: 52241 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.0324. Min Act: -0.1700
Data Index: 1168412 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2824. Min Range: -8.2824
Max Act: 8.0949. Min Act: -0.1700
Data Index: 2585537 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19