Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1367 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.5136. Min Act: -0.1700
Data Index: 4476269 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.4511. Min Act: -0.1700
Data Index: 4940662 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.4199. Min Act: -0.1700
Data Index: 7159501 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.4199. Min Act: -0.1700
Data Index: 5615721 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.3886. Min Act: -0.1700
Data Index: 8655152 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.3886. Min Act: -0.1700
Data Index: 2641490 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.3261. Min Act: -0.1700
Data Index: 5635095 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.2949. Min Act: -0.1700
Data Index: 418817 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.3574. Min Act: -0.1700
Data Index: 5250006 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.3261. Min Act: -0.1700
Data Index: 3255442 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.2949. Min Act: -0.1700
Data Index: 2221265 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.2636. Min Act: -0.1700
Data Index: 6208329 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.2636. Min Act: -0.1700
Data Index: 2564909 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.2636. Min Act: -0.1700
Data Index: 1884711 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.2636. Min Act: -0.1700
Data Index: 6590480 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.2636. Min Act: -0.1700
Data Index: 2568971 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.2324. Min Act: -0.1700
Data Index: 2194777 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.2324. Min Act: -0.1700
Data Index: 6942213 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.2324. Min Act: -0.1700
Data Index: 6256530 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5136. Min Range: -5.5136
Max Act: 5.2324. Min Act: -0.1700
Data Index: 7272864 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19