Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2548 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0866. Min Range: -7.0866
Max Act: 7.0866. Min Act: -0.1700
Data Index: 3858822 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.8366. Min Act: -0.1700
Data Index: 1731271 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.7741. Min Act: -0.1700
Data Index: 5900825 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.7741. Min Act: -0.1700
Data Index: 2395672 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.7116. Min Act: -0.1700
Data Index: 981677 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.6179. Min Act: -0.1700
Data Index: 3573839 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.6491. Min Act: -0.1700
Data Index: 1079824 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.6179. Min Act: -0.1700
Data Index: 1466508 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.6179. Min Act: -0.1700
Data Index: 3619254 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.5866. Min Act: -0.1700
Data Index: 7665430 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.5866. Min Act: -0.1700
Data Index: 3367264 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.5554. Min Act: -0.1700
Data Index: 967777 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.5554. Min Act: -0.1700
Data Index: 3011937 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.5554. Min Act: -0.1700
Data Index: 2938264 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.5554. Min Act: -0.1700
Data Index: 5161134 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.5554. Min Act: -0.1700
Data Index: 1965940 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.5241. Min Act: -0.1700
Data Index: 5868633 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.4929. Min Act: -0.1700
Data Index: 7911350 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.5241. Min Act: -0.1700
Data Index: 941801 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0866. Min Range: -7.0866
Max Act: 6.5241. Min Act: -0.1700
Data Index: 2895776 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19