Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4088 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6139. Min Range: -8.6139
Max Act: 8.6139. Min Act: -0.1700
Data Index: 8478673 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6139. Min Range: -8.6139
Max Act: 8.4264. Min Act: -0.1700
Data Index: 5273290 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6139. Min Range: -8.6139
Max Act: 8.3639. Min Act: -0.1700
Data Index: 3430433 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6139. Min Range: -8.6139
Max Act: 8.2389. Min Act: -0.1700
Data Index: 1988299 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6139. Min Range: -8.6139
Max Act: 8.0514. Min Act: -0.1700
Data Index: 6436693 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6139. Min Range: -8.6139
Max Act: 8.0514. Min Act: -0.1700
Data Index: 3458998 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6139. Min Range: -8.6139
Max Act: 7.9577. Min Act: -0.1700
Data Index: 8485097 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6139. Min Range: -8.6139
Max Act: 7.9264. Min Act: -0.1700
Data Index: 7826492 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6139. Min Range: -8.6139
Max Act: 7.8952. Min Act: -0.1700
Data Index: 7447888 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6139. Min Range: -8.6139
Max Act: 7.8952. Min Act: -0.1700
Data Index: 44070 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6139. Min Range: -8.6139
Max Act: 7.8639. Min Act: -0.1700
Data Index: 7015035 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6139. Min Range: -8.6139
Max Act: 7.8327. Min Act: -0.1700
Data Index: 3533264 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6139. Min Range: -8.6139
Max Act: 7.8014. Min Act: -0.1700
Data Index: 8178695 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6139. Min Range: -8.6139
Max Act: 7.7389. Min Act: -0.1700
Data Index: 6387585 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6139. Min Range: -8.6139
Max Act: 7.6764. Min Act: -0.1700
Data Index: 4892968 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6139. Min Range: -8.6139
Max Act: 7.6764. Min Act: -0.1700
Data Index: 4306892 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6139. Min Range: -8.6139
Max Act: 7.6452. Min Act: -0.1700
Data Index: 323565 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6139. Min Range: -8.6139
Max Act: 7.6139. Min Act: -0.1700
Data Index: 3856201 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6139. Min Range: -8.6139
Max Act: 7.6452. Min Act: -0.1700
Data Index: 2344894 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6139. Min Range: -8.6139
Max Act: 7.5827. Min Act: -0.1700
Data Index: 107383 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19