Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5947 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.5003. Min Act: -0.1700
Data Index: 4184680 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.4691. Min Act: -0.1700
Data Index: 2166510 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.4378. Min Act: -0.1700
Data Index: 8269694 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.4378. Min Act: -0.1700
Data Index: 1774707 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.4378. Min Act: -0.1700
Data Index: 1941259 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.4378. Min Act: -0.1700
Data Index: 1052513 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.4691. Min Act: -0.1700
Data Index: 7135771 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.4066. Min Act: -0.1700
Data Index: 1634709 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.4066. Min Act: -0.1700
Data Index: 1996216 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.4066. Min Act: -0.1700
Data Index: 2835491 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.3753. Min Act: -0.1700
Data Index: 2967977 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.3753. Min Act: -0.1700
Data Index: 14907 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.3753. Min Act: -0.1700
Data Index: 7197568 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.3753. Min Act: -0.1700
Data Index: 700207 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.3753. Min Act: -0.1700
Data Index: 5183396 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.3753. Min Act: -0.1700
Data Index: 6696253 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.3753. Min Act: -0.1700
Data Index: 4143664 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.3753. Min Act: -0.1700
Data Index: 4346929 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.3441. Min Act: -0.1700
Data Index: 4718594 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5003. Min Range: -4.5003
Max Act: 4.3441. Min Act: -0.1700
Data Index: 6054531 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19