Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1657 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.6517. Min Act: -0.1700
Data Index: 5794560 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.6830. Min Act: -0.1700
Data Index: 7049741 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.6517. Min Act: -0.1700
Data Index: 3893038 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.6204. Min Act: -0.1700
Data Index: 8648658 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.6204. Min Act: -0.1700
Data Index: 7043707 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5578. Min Act: -0.1700
Data Index: 133683 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5891. Min Act: -0.1700
Data Index: 4101023 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5265. Min Act: -0.1700
Data Index: 3220105 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.4952. Min Act: -0.1700
Data Index: 2063708 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5265. Min Act: -0.1700
Data Index: 8594435 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5265. Min Act: -0.1700
Data Index: 6472519 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5265. Min Act: -0.1700
Data Index: 5542346 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5265. Min Act: -0.1700
Data Index: 727718 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.4952. Min Act: -0.1700
Data Index: 2055105 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.4952. Min Act: -0.1700
Data Index: 2163140 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.4952. Min Act: -0.1700
Data Index: 2193673 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.4952. Min Act: -0.1700
Data Index: 2365605 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.4952. Min Act: -0.1700
Data Index: 2745294 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.4952. Min Act: -0.1700
Data Index: 2818337 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.4952. Min Act: -0.1700
Data Index: 2863985 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19