Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 551 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3271. Min Range: -6.3271
Max Act: 6.3271. Min Act: -0.1700
Data Index: 11763 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3271. Min Range: -6.3271
Max Act: 6.2334. Min Act: -0.1700
Data Index: 5921786 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3271. Min Range: -6.3271
Max Act: 6.2021. Min Act: -0.1700
Data Index: 748305 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3271. Min Range: -6.3271
Max Act: 6.1084. Min Act: -0.1700
Data Index: 4485142 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3271. Min Range: -6.3271
Max Act: 6.0459. Min Act: -0.1700
Data Index: 2169009 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3271. Min Range: -6.3271
Max Act: 6.1084. Min Act: -0.1700
Data Index: 4764225 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3271. Min Range: -6.3271
Max Act: 6.0146. Min Act: -0.1700
Data Index: 7301001 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3271. Min Range: -6.3271
Max Act: 6.0146. Min Act: -0.1700
Data Index: 5636573 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3271. Min Range: -6.3271
Max Act: 6.0146. Min Act: -0.1700
Data Index: 807005 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3271. Min Range: -6.3271
Max Act: 6.0146. Min Act: -0.1700
Data Index: 6391187 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3271. Min Range: -6.3271
Max Act: 5.9834. Min Act: -0.1700
Data Index: 6320816 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3271. Min Range: -6.3271
Max Act: 5.9834. Min Act: -0.1700
Data Index: 4530711 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3271. Min Range: -6.3271
Max Act: 5.9521. Min Act: -0.1700
Data Index: 6788810 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3271. Min Range: -6.3271
Max Act: 6.0146. Min Act: -0.1700
Data Index: 8048332 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3271. Min Range: -6.3271
Max Act: 5.9834. Min Act: -0.1700
Data Index: 8054395 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3271. Min Range: -6.3271
Max Act: 5.9521. Min Act: -0.1700
Data Index: 4249183 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3271. Min Range: -6.3271
Max Act: 5.9521. Min Act: -0.1700
Data Index: 2241111 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3271. Min Range: -6.3271
Max Act: 5.9521. Min Act: -0.1700
Data Index: 2435352 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3271. Min Range: -6.3271
Max Act: 5.9209. Min Act: -0.1700
Data Index: 7300994 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3271. Min Range: -6.3271
Max Act: 5.9209. Min Act: -0.1700
Data Index: 5098187 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19