Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4071 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0162. Min Range: -8.0162
Max Act: 8.0162. Min Act: -0.1700
Data Index: 744254 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.4225. Min Act: -0.1700
Data Index: 7049054 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.3287. Min Act: -0.1700
Data Index: 1951434 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.2975. Min Act: -0.1700
Data Index: 6105494 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.2975. Min Act: -0.1700
Data Index: 984024 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.2975. Min Act: -0.1700
Data Index: 3729383 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.2350. Min Act: -0.1700
Data Index: 3614241 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.2037. Min Act: -0.1700
Data Index: 8709064 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.2037. Min Act: -0.1700
Data Index: 6186016 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.2037. Min Act: -0.1700
Data Index: 7559831 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.2350. Min Act: -0.1700
Data Index: 7136476 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.2037. Min Act: -0.1700
Data Index: 6322676 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.1412. Min Act: -0.1700
Data Index: 1641921 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.1100. Min Act: -0.1700
Data Index: 3670872 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.1100. Min Act: -0.1700
Data Index: 6236090 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.1100. Min Act: -0.1700
Data Index: 1795361 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.0787. Min Act: -0.1700
Data Index: 383904 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.0787. Min Act: -0.1700
Data Index: 1489626 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.0787. Min Act: -0.1700
Data Index: 3443863 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0162. Min Range: -8.0162
Max Act: 7.0475. Min Act: -0.1700
Data Index: 2073183 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19