Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.9002. Min Act: -0.1700
Data Index: 3453952 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.5565. Min Act: -0.1700
Data Index: 2696821 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.5565. Min Act: -0.1700
Data Index: 3747068 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.5252. Min Act: -0.1700
Data Index: 8762774 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.3690. Min Act: -0.1700
Data Index: 7381743 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.4002. Min Act: -0.1700
Data Index: 7395603 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.4002. Min Act: -0.1700
Data Index: 3546285 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.3377. Min Act: -0.1700
Data Index: 1297940 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.3065. Min Act: -0.1700
Data Index: 5918456 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.2752. Min Act: -0.1700
Data Index: 4213388 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.2440. Min Act: -0.1700
Data Index: 2796082 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.1815. Min Act: -0.1700
Data Index: 6112014 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.1815. Min Act: -0.1700
Data Index: 5227098 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.1815. Min Act: -0.1700
Data Index: 4862638 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.1502. Min Act: -0.1700
Data Index: 962523 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.0877. Min Act: -0.1700
Data Index: 2619420 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.0565. Min Act: -0.1700
Data Index: 4412137 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.0252. Min Act: -0.1700
Data Index: 1001538 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.0565. Min Act: -0.1700
Data Index: 1564769 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9002. Min Range: -6.9002
Max Act: 6.0252. Min Act: -0.1700
Data Index: 2759763 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19