Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1645 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.6624. Min Act: -0.1700
Data Index: 5462123 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.4436. Min Act: -0.1700
Data Index: 4071427 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.4124. Min Act: -0.1700
Data Index: 8719411 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.3499. Min Act: -0.1700
Data Index: 2971423 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.3499. Min Act: -0.1700
Data Index: 6235720 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.3499. Min Act: -0.1700
Data Index: 6297537 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.3186. Min Act: -0.1700
Data Index: 8666562 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.3186. Min Act: -0.1700
Data Index: 3480385 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.3186. Min Act: -0.1700
Data Index: 2747208 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.2874. Min Act: -0.1700
Data Index: 7698744 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.3186. Min Act: -0.1700
Data Index: 7627882 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.2874. Min Act: -0.1700
Data Index: 3348222 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.2874. Min Act: -0.1700
Data Index: 6662387 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.2874. Min Act: -0.1700
Data Index: 604709 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.2874. Min Act: -0.1700
Data Index: 3864706 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.2874. Min Act: -0.1700
Data Index: 3862380 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.2561. Min Act: -0.1700
Data Index: 6720069 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.2561. Min Act: -0.1700
Data Index: 7553327 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.2248. Min Act: -0.1700
Data Index: 1130904 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6624. Min Range: -4.6624
Max Act: 4.2561. Min Act: -0.1700
Data Index: 248449 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19