Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4771 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.3318. Min Act: -0.1700
Data Index: 1154076 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.3318. Min Act: -0.1700
Data Index: 3614756 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.3004. Min Act: -0.1700
Data Index: 133331 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.3004. Min Act: -0.1700
Data Index: 7429344 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.2690. Min Act: -0.1700
Data Index: 4480174 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.2690. Min Act: -0.1700
Data Index: 3784010 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.2690. Min Act: -0.1700
Data Index: 2653364 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.2690. Min Act: -0.1700
Data Index: 7108295 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.2690. Min Act: -0.1700
Data Index: 7284770 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.2376. Min Act: -0.1700
Data Index: 7477379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.2062. Min Act: -0.1700
Data Index: 6050547 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.2062. Min Act: -0.1700
Data Index: 2633631 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.2062. Min Act: -0.1700
Data Index: 6443069 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.2062. Min Act: -0.1700
Data Index: 4890159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.2062. Min Act: -0.1700
Data Index: 1979806 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.1747. Min Act: -0.1700
Data Index: 4316938 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.1747. Min Act: -0.1700
Data Index: 5095918 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.1747. Min Act: -0.1700
Data Index: 5232411 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.1747. Min Act: -0.1700
Data Index: 5413191 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3318. Min Range: -3.3318
Max Act: 3.1747. Min Act: -0.1700
Data Index: 5429715 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19