Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1681 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.9881. Min Act: -0.1700
Data Index: 6839919 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.9568. Min Act: -0.1700
Data Index: 2725494 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.9256. Min Act: -0.1700
Data Index: 3654876 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.8318. Min Act: -0.1700
Data Index: 1451420 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.8006. Min Act: -0.1700
Data Index: 5276114 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.6756. Min Act: -0.1700
Data Index: 7542122 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.6756. Min Act: -0.1700
Data Index: 4944863 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.6443. Min Act: -0.1700
Data Index: 4362845 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.6131. Min Act: -0.1700
Data Index: 7324120 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.5818. Min Act: -0.1700
Data Index: 7033423 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.5506. Min Act: -0.1700
Data Index: 755409 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.5193. Min Act: -0.1700
Data Index: 6820806 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.5506. Min Act: -0.1700
Data Index: 8576476 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.5506. Min Act: -0.1700
Data Index: 6503718 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.5193. Min Act: -0.1700
Data Index: 4026319 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.5193. Min Act: -0.1700
Data Index: 7387064 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.4881. Min Act: -0.1700
Data Index: 5351669 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.4881. Min Act: -0.1700
Data Index: 7210215 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.4881. Min Act: -0.1700
Data Index: 2148697 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9881. Min Range: -5.9881
Max Act: 5.4881. Min Act: -0.1700
Data Index: 6971402 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19