Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2393 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.9982. Min Act: -0.1700
Data Index: 4023826 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.9982. Min Act: -0.1700
Data Index: 3014733 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.9357. Min Act: -0.1700
Data Index: 4301363 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.9357. Min Act: -0.1700
Data Index: 713348 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.9357. Min Act: -0.1700
Data Index: 8333115 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.9045. Min Act: -0.1700
Data Index: 1715858 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.9357. Min Act: -0.1700
Data Index: 3258821 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.8732. Min Act: -0.1700
Data Index: 3794454 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.8732. Min Act: -0.1700
Data Index: 785456 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.8420. Min Act: -0.1700
Data Index: 7828076 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.8420. Min Act: -0.1700
Data Index: 7464214 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.8420. Min Act: -0.1700
Data Index: 3049343 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.8107. Min Act: -0.1700
Data Index: 6867168 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.8420. Min Act: -0.1700
Data Index: 5886461 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.7795. Min Act: -0.1700
Data Index: 1063802 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.8420. Min Act: -0.1700
Data Index: 1697363 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.8107. Min Act: -0.1700
Data Index: 7833139 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.7795. Min Act: -0.1700
Data Index: 5427489 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.7795. Min Act: -0.1700
Data Index: 3887632 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9982. Min Range: -5.9982
Max Act: 5.7795. Min Act: -0.1700
Data Index: 5807574 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19