Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3561 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.8130. Min Act: -0.1700
Data Index: 7419321 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.4693. Min Act: -0.1700
Data Index: 1531589 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.4693. Min Act: -0.1700
Data Index: 519088 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.4693. Min Act: -0.1700
Data Index: 612546 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.4693. Min Act: -0.1700
Data Index: 4233650 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.4068. Min Act: -0.1700
Data Index: 8186327 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3755. Min Act: -0.1700
Data Index: 705232 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3443. Min Act: -0.1700
Data Index: 469538 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3443. Min Act: -0.1700
Data Index: 4318899 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3443. Min Act: -0.1700
Data Index: 7722751 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3130. Min Act: -0.1700
Data Index: 7611212 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.2818. Min Act: -0.1700
Data Index: 2195909 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.2818. Min Act: -0.1700
Data Index: 7535900 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.2505. Min Act: -0.1700
Data Index: 855178 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.2505. Min Act: -0.1700
Data Index: 5946656 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.2193. Min Act: -0.1700
Data Index: 7554047 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.2193. Min Act: -0.1700
Data Index: 4107220 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.2193. Min Act: -0.1700
Data Index: 4366262 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.1880. Min Act: -0.1700
Data Index: 4702937 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.1880. Min Act: -0.1700
Data Index: 6862061 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19