Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4467 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0022. Min Range: -7.0022
Max Act: 7.0022. Min Act: -0.1700
Data Index: 6727361 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0022. Min Range: -7.0022
Max Act: 7.0022. Min Act: -0.1700
Data Index: 7105414 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0022. Min Range: -7.0022
Max Act: 7.0022. Min Act: -0.1700
Data Index: 3062615 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.9710. Min Act: -0.1700
Data Index: 2724303 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.9710. Min Act: -0.1700
Data Index: 8700723 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.9397. Min Act: -0.1700
Data Index: 6547070 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.9085. Min Act: -0.1700
Data Index: 2671847 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.8772. Min Act: -0.1700
Data Index: 5101009 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.9085. Min Act: -0.1700
Data Index: 1582737 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.8460. Min Act: -0.1700
Data Index: 6634656 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.8460. Min Act: -0.1700
Data Index: 4379870 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.8147. Min Act: -0.1700
Data Index: 1009443 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.8147. Min Act: -0.1700
Data Index: 4905649 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.8460. Min Act: -0.1700
Data Index: 7875175 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.8147. Min Act: -0.1700
Data Index: 6800598 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.7835. Min Act: -0.1700
Data Index: 8281906 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.7835. Min Act: -0.1700
Data Index: 4085654 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.7835. Min Act: -0.1700
Data Index: 1823665 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.7835. Min Act: -0.1700
Data Index: 887143 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0022. Min Range: -7.0022
Max Act: 6.7522. Min Act: -0.1700
Data Index: 4894651 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19