Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4897 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0159. Min Range: -7.0159
Max Act: 7.0159. Min Act: -0.1700
Data Index: 5132675 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7971. Min Act: -0.1700
Data Index: 1353803 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7971. Min Act: -0.1700
Data Index: 4318524 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7659. Min Act: -0.1700
Data Index: 7247625 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.6721. Min Act: -0.1700
Data Index: 3944311 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.6409. Min Act: -0.1700
Data Index: 2419542 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.6409. Min Act: -0.1700
Data Index: 5232729 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.6409. Min Act: -0.1700
Data Index: 363281 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.6409. Min Act: -0.1700
Data Index: 3914150 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.6096. Min Act: -0.1700
Data Index: 7773071 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.6096. Min Act: -0.1700
Data Index: 742592 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.5471. Min Act: -0.1700
Data Index: 131958 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.5471. Min Act: -0.1700
Data Index: 3656033 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.4846. Min Act: -0.1700
Data Index: 3656031 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.4846. Min Act: -0.1700
Data Index: 1627203 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.4846. Min Act: -0.1700
Data Index: 4320541 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.4846. Min Act: -0.1700
Data Index: 1378532 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.4221. Min Act: -0.1700
Data Index: 3867086 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.4534. Min Act: -0.1700
Data Index: 6472135 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.4534. Min Act: -0.1700
Data Index: 7591360 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19