Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5782 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.4148. Min Act: -0.1700
Data Index: 8769542 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3985. Min Act: -0.1700
Data Index: 8701312 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3330. Min Act: -0.1700
Data Index: 8805335 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3494. Min Act: -0.1700
Data Index: 7041489 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3166. Min Act: -0.1700
Data Index: 4981833 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3002. Min Act: -0.1700
Data Index: 7183410 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3166. Min Act: -0.1700
Data Index: 5708264 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3002. Min Act: -0.1700
Data Index: 4480171 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2837. Min Act: -0.1700
Data Index: 2309146 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2672. Min Act: -0.1700
Data Index: 333880 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3002. Min Act: -0.1700
Data Index: 8018293 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3002. Min Act: -0.1700
Data Index: 6676610 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2837. Min Act: -0.1700
Data Index: 651473 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2837. Min Act: -0.1700
Data Index: 5206627 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2672. Min Act: -0.1700
Data Index: 3160337 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2672. Min Act: -0.1700
Data Index: 6466634 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2672. Min Act: -0.1700
Data Index: 7462488 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2672. Min Act: -0.1700
Data Index: 1659336 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2672. Min Act: -0.1700
Data Index: 8109031 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2672. Min Act: -0.1700
Data Index: 1515732 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19