Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5820 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3860. Min Range: -6.3860
Max Act: 6.3235. Min Act: -0.1700
Data Index: 4332772 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3860. Min Range: -6.3860
Max Act: 6.3860. Min Act: -0.1700
Data Index: 1395410 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3860. Min Range: -6.3860
Max Act: 6.1672. Min Act: -0.1700
Data Index: 6022024 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3860. Min Range: -6.3860
Max Act: 6.0735. Min Act: -0.1700
Data Index: 3999602 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3860. Min Range: -6.3860
Max Act: 6.0422. Min Act: -0.1700
Data Index: 7096014 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3860. Min Range: -6.3860
Max Act: 5.9485. Min Act: -0.1700
Data Index: 1216069 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3860. Min Range: -6.3860
Max Act: 5.8860. Min Act: -0.1700
Data Index: 6069622 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3860. Min Range: -6.3860
Max Act: 5.8547. Min Act: -0.1700
Data Index: 4536979 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3860. Min Range: -6.3860
Max Act: 5.8547. Min Act: -0.1700
Data Index: 4796502 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3860. Min Range: -6.3860
Max Act: 5.8235. Min Act: -0.1700
Data Index: 1334725 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3860. Min Range: -6.3860
Max Act: 5.8235. Min Act: -0.1700
Data Index: 952500 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3860. Min Range: -6.3860
Max Act: 5.8235. Min Act: -0.1700
Data Index: 3106836 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3860. Min Range: -6.3860
Max Act: 5.7922. Min Act: -0.1700
Data Index: 2897038 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3860. Min Range: -6.3860
Max Act: 5.8235. Min Act: -0.1700
Data Index: 2025337 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3860. Min Range: -6.3860
Max Act: 5.7922. Min Act: -0.1700
Data Index: 1201083 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3860. Min Range: -6.3860
Max Act: 5.7922. Min Act: -0.1700
Data Index: 8577156 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3860. Min Range: -6.3860
Max Act: 5.8235. Min Act: -0.1700
Data Index: 6367950 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3860. Min Range: -6.3860
Max Act: 5.7610. Min Act: -0.1700
Data Index: 278516 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3860. Min Range: -6.3860
Max Act: 5.7297. Min Act: -0.1700
Data Index: 6715146 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3860. Min Range: -6.3860
Max Act: 5.7297. Min Act: -0.1700
Data Index: 2973400 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19