Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3560 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.4777. Min Act: -0.1700
Data Index: 1221015 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.4452. Min Act: -0.1700
Data Index: 3722944 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.4290. Min Act: -0.1700
Data Index: 6539908 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.3800. Min Act: -0.1700
Data Index: 7323098 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.3800. Min Act: -0.1700
Data Index: 4748848 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.3800. Min Act: -0.1700
Data Index: 334165 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.3473. Min Act: -0.1700
Data Index: 8136950 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.3473. Min Act: -0.1700
Data Index: 2781695 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.3473. Min Act: -0.1700
Data Index: 8595331 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.3473. Min Act: -0.1700
Data Index: 6096204 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.3473. Min Act: -0.1700
Data Index: 5593279 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.3309. Min Act: -0.1700
Data Index: 549387 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.3145. Min Act: -0.1700
Data Index: 4388104 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.3309. Min Act: -0.1700
Data Index: 1186048 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.3309. Min Act: -0.1700
Data Index: 2407827 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.3145. Min Act: -0.1700
Data Index: 1400373 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.3145. Min Act: -0.1700
Data Index: 8127162 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.2980. Min Act: -0.1700
Data Index: 4604018 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.2980. Min Act: -0.1700
Data Index: 2477118 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4777. Min Range: -2.4777
Max Act: 2.2980. Min Act: -0.1700
Data Index: 3289534 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19