Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 49 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.8749. Min Act: -0.1700
Data Index: 4046518 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.7499. Min Act: -0.1700
Data Index: 988417 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.6874. Min Act: -0.1700
Data Index: 988406 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.6561. Min Act: -0.1700
Data Index: 6484920 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.6561. Min Act: -0.1700
Data Index: 4923907 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.5311. Min Act: -0.1700
Data Index: 4933434 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.4999. Min Act: -0.1700
Data Index: 5079240 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.4999. Min Act: -0.1700
Data Index: 8756014 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.4686. Min Act: -0.1700
Data Index: 2990864 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.4686. Min Act: -0.1700
Data Index: 6420238 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.4374. Min Act: -0.1700
Data Index: 278117 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.4374. Min Act: -0.1700
Data Index: 5255443 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.4374. Min Act: -0.1700
Data Index: 3606195 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.4374. Min Act: -0.1700
Data Index: 7923211 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.4374. Min Act: -0.1700
Data Index: 2858979 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.3749. Min Act: -0.1700
Data Index: 8484734 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.3749. Min Act: -0.1700
Data Index: 3365122 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.3749. Min Act: -0.1700
Data Index: 846381 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.3436. Min Act: -0.1700
Data Index: 2263506 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8749. Min Range: -5.8749
Max Act: 5.3436. Min Act: -0.1700
Data Index: 6800053 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19