Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6342 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2650. Min Range: -7.2650
Max Act: 7.2650. Min Act: -0.1700
Data Index: 6921169 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.9525. Min Act: -0.1700
Data Index: 3868052 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.8588. Min Act: -0.1700
Data Index: 8267458 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.8275. Min Act: -0.1700
Data Index: 6066936 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.8275. Min Act: -0.1700
Data Index: 1343744 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.8275. Min Act: -0.1700
Data Index: 6182970 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.7650. Min Act: -0.1700
Data Index: 5776443 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.7963. Min Act: -0.1700
Data Index: 2557600 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.7650. Min Act: -0.1700
Data Index: 1091853 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.7338. Min Act: -0.1700
Data Index: 1123251 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.7025. Min Act: -0.1700
Data Index: 3479484 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.7338. Min Act: -0.1700
Data Index: 3466335 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.7025. Min Act: -0.1700
Data Index: 5895936 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.7025. Min Act: -0.1700
Data Index: 6323473 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.7025. Min Act: -0.1700
Data Index: 6350029 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.7025. Min Act: -0.1700
Data Index: 2315885 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.6400. Min Act: -0.1700
Data Index: 3384726 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.6713. Min Act: -0.1700
Data Index: 5953084 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.6400. Min Act: -0.1700
Data Index: 3256421 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.6713. Min Act: -0.1700
Data Index: 8037914 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19