Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5043 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.8646. Min Act: -0.1700
Data Index: 5725140 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.4896. Min Act: -0.1700
Data Index: 4202435 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.3959. Min Act: -0.1700
Data Index: 5002679 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.3959. Min Act: -0.1700
Data Index: 5951467 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.3646. Min Act: -0.1700
Data Index: 2279061 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.3646. Min Act: -0.1700
Data Index: 4915301 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.3646. Min Act: -0.1700
Data Index: 5878003 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.3334. Min Act: -0.1700
Data Index: 1536086 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.3334. Min Act: -0.1700
Data Index: 2301631 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.3021. Min Act: -0.1700
Data Index: 7693825 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.2709. Min Act: -0.1700
Data Index: 5560945 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.2709. Min Act: -0.1700
Data Index: 8048222 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.2709. Min Act: -0.1700
Data Index: 4204926 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.2396. Min Act: -0.1700
Data Index: 894975 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.2396. Min Act: -0.1700
Data Index: 2595073 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.2396. Min Act: -0.1700
Data Index: 1217069 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.2084. Min Act: -0.1700
Data Index: 4321506 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.1771. Min Act: -0.1700
Data Index: 2653187 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.1771. Min Act: -0.1700
Data Index: 3028052 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8646. Min Range: -6.8646
Max Act: 6.1771. Min Act: -0.1700
Data Index: 3076668 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19