Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2709 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5624. Min Range: -8.5624
Max Act: 8.5624. Min Act: -0.1700
Data Index: 1261312 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5624. Min Range: -8.5624
Max Act: 8.3749. Min Act: -0.1700
Data Index: 5939950 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5624. Min Range: -8.5624
Max Act: 8.3124. Min Act: -0.1700
Data Index: 2659564 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5624. Min Range: -8.5624
Max Act: 8.1874. Min Act: -0.1700
Data Index: 4652040 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5624. Min Range: -8.5624
Max Act: 8.0624. Min Act: -0.1700
Data Index: 7690380 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5624. Min Range: -8.5624
Max Act: 8.0624. Min Act: -0.1700
Data Index: 3865101 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5624. Min Range: -8.5624
Max Act: 8.0624. Min Act: -0.1700
Data Index: 5425815 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5624. Min Range: -8.5624
Max Act: 8.0624. Min Act: -0.1700
Data Index: 4233461 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5624. Min Range: -8.5624
Max Act: 7.9999. Min Act: -0.1700
Data Index: 6429884 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5624. Min Range: -8.5624
Max Act: 7.9374. Min Act: -0.1700
Data Index: 4197126 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5624. Min Range: -8.5624
Max Act: 7.9999. Min Act: -0.1700
Data Index: 2928056 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5624. Min Range: -8.5624
Max Act: 7.9999. Min Act: -0.1700
Data Index: 7779150 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5624. Min Range: -8.5624
Max Act: 7.9374. Min Act: -0.1700
Data Index: 5708885 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5624. Min Range: -8.5624
Max Act: 7.9374. Min Act: -0.1700
Data Index: 3993053 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5624. Min Range: -8.5624
Max Act: 7.9374. Min Act: -0.1700
Data Index: 4865743 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5624. Min Range: -8.5624
Max Act: 7.8749. Min Act: -0.1700
Data Index: 6625192 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5624. Min Range: -8.5624
Max Act: 7.8749. Min Act: -0.1700
Data Index: 6335241 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5624. Min Range: -8.5624
Max Act: 7.8749. Min Act: -0.1700
Data Index: 4782015 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5624. Min Range: -8.5624
Max Act: 7.8124. Min Act: -0.1700
Data Index: 2686597 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5624. Min Range: -8.5624
Max Act: 7.8124. Min Act: -0.1700
Data Index: 1716720 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19