Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4457 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.2809. Min Act: -0.1700
Data Index: 5060306 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.2809. Min Act: -0.1700
Data Index: 8737911 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.2652. Min Act: -0.1700
Data Index: 5943637 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.2338. Min Act: -0.1700
Data Index: 3837083 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.2338. Min Act: -0.1700
Data Index: 5462375 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.1866. Min Act: -0.1700
Data Index: 6830143 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.1866. Min Act: -0.1700
Data Index: 5772095 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.1236. Min Act: -0.1700
Data Index: 3830644 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.1394. Min Act: -0.1700
Data Index: 4012213 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.1079. Min Act: -0.1700
Data Index: 7826860 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.1236. Min Act: -0.1700
Data Index: 1558378 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.1079. Min Act: -0.1700
Data Index: 7778657 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0921. Min Act: -0.1700
Data Index: 2484379 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.1079. Min Act: -0.1700
Data Index: 4179738 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.1236. Min Act: -0.1700
Data Index: 4011596 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.1079. Min Act: -0.1700
Data Index: 3725078 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0921. Min Act: -0.1700
Data Index: 260463 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0921. Min Act: -0.1700
Data Index: 1120585 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0921. Min Act: -0.1700
Data Index: 3861665 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2809. Min Range: -3.2809
Max Act: 3.0921. Min Act: -0.1700
Data Index: 4889780 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19