Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3110 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.5937. Min Act: -0.1700
Data Index: 3685744 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.5937. Min Act: -0.1700
Data Index: 5228529 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.5624. Min Act: -0.1700
Data Index: 4454991 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.5624. Min Act: -0.1700
Data Index: 386599 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.5312. Min Act: -0.1700
Data Index: 5745300 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.4999. Min Act: -0.1700
Data Index: 6178410 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.4999. Min Act: -0.1700
Data Index: 2358527 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.4999. Min Act: -0.1700
Data Index: 3706770 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.4687. Min Act: -0.1700
Data Index: 7097432 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.4687. Min Act: -0.1700
Data Index: 6224284 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.4687. Min Act: -0.1700
Data Index: 5581755 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.4374. Min Act: -0.1700
Data Index: 907510 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.4062. Min Act: -0.1700
Data Index: 8193150 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.3749. Min Act: -0.1700
Data Index: 3978558 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.3749. Min Act: -0.1700
Data Index: 5636946 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.3749. Min Act: -0.1700
Data Index: 4942408 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.3749. Min Act: -0.1700
Data Index: 3132798 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.3749. Min Act: -0.1700
Data Index: 3110925 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.3437. Min Act: -0.1700
Data Index: 8343270 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.3124. Min Act: -0.1700
Data Index: 5421587 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19