Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3776 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4335. Min Range: -6.4335
Max Act: 6.4335. Min Act: -0.1700
Data Index: 4264144 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4335. Min Range: -6.4335
Max Act: 6.3397. Min Act: -0.1700
Data Index: 204100 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4335. Min Range: -6.4335
Max Act: 6.2460. Min Act: -0.1700
Data Index: 2483950 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4335. Min Range: -6.4335
Max Act: 6.0897. Min Act: -0.1700
Data Index: 4582916 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4335. Min Range: -6.4335
Max Act: 6.0897. Min Act: -0.1700
Data Index: 3742409 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4335. Min Range: -6.4335
Max Act: 6.0897. Min Act: -0.1700
Data Index: 8052787 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4335. Min Range: -6.4335
Max Act: 6.0897. Min Act: -0.1700
Data Index: 8511357 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4335. Min Range: -6.4335
Max Act: 6.0585. Min Act: -0.1700
Data Index: 1175249 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4335. Min Range: -6.4335
Max Act: 5.9960. Min Act: -0.1700
Data Index: 8752310 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4335. Min Range: -6.4335
Max Act: 6.0272. Min Act: -0.1700
Data Index: 1400749 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4335. Min Range: -6.4335
Max Act: 5.9647. Min Act: -0.1700
Data Index: 6930604 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4335. Min Range: -6.4335
Max Act: 5.9647. Min Act: -0.1700
Data Index: 4019658 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4335. Min Range: -6.4335
Max Act: 5.9335. Min Act: -0.1700
Data Index: 1194101 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4335. Min Range: -6.4335
Max Act: 5.9647. Min Act: -0.1700
Data Index: 1603638 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4335. Min Range: -6.4335
Max Act: 5.9335. Min Act: -0.1700
Data Index: 8570598 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4335. Min Range: -6.4335
Max Act: 5.9022. Min Act: -0.1700
Data Index: 5886584 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4335. Min Range: -6.4335
Max Act: 5.9022. Min Act: -0.1700
Data Index: 8397132 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4335. Min Range: -6.4335
Max Act: 5.9022. Min Act: -0.1700
Data Index: 4714935 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4335. Min Range: -6.4335
Max Act: 5.9022. Min Act: -0.1700
Data Index: 7677243 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4335. Min Range: -6.4335
Max Act: 5.9022. Min Act: -0.1700
Data Index: 2983133 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19