Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 895 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.4660. Min Act: -0.1700
Data Index: 1470355 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.4347. Min Act: -0.1700
Data Index: 1944110 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.4033. Min Act: -0.1700
Data Index: 5061946 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.4033. Min Act: -0.1700
Data Index: 8719 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.4033. Min Act: -0.1700
Data Index: 7531040 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.3720. Min Act: -0.1700
Data Index: 7193880 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.3406. Min Act: -0.1700
Data Index: 1219041 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.3406. Min Act: -0.1700
Data Index: 8432492 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.3092. Min Act: -0.1700
Data Index: 5371692 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.3092. Min Act: -0.1700
Data Index: 2935488 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.3092. Min Act: -0.1700
Data Index: 5859243 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.2778. Min Act: -0.1700
Data Index: 7863112 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.2307. Min Act: -0.1700
Data Index: 8543389 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.2150. Min Act: -0.1700
Data Index: 6434907 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.2307. Min Act: -0.1700
Data Index: 1278507 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.2307. Min Act: -0.1700
Data Index: 8056543 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.2307. Min Act: -0.1700
Data Index: 5805329 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.1992. Min Act: -0.1700
Data Index: 1478479 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.1678. Min Act: -0.1700
Data Index: 5267434 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4660. Min Range: -3.4660
Max Act: 3.1678. Min Act: -0.1700
Data Index: 7565473 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19