Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 283 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0624. Min Range: -5.0624
Max Act: 5.0624. Min Act: -0.1700
Data Index: 4883265 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0624. Min Range: -5.0624
Max Act: 5.0624. Min Act: -0.1700
Data Index: 5852977 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0624. Min Range: -5.0624
Max Act: 5.0312. Min Act: -0.1700
Data Index: 7725845 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.9687. Min Act: -0.1700
Data Index: 684830 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.9687. Min Act: -0.1700
Data Index: 13395 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.9687. Min Act: -0.1700
Data Index: 7405256 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.9374. Min Act: -0.1695
Data Index: 1360044 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.9374. Min Act: -0.1700
Data Index: 5654422 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.9374. Min Act: -0.1700
Data Index: 13394 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.9062. Min Act: -0.1700
Data Index: 7851151 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.9062. Min Act: -0.1700
Data Index: 7851152 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.9062. Min Act: -0.1700
Data Index: 259367 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.9062. Min Act: -0.1700
Data Index: 8418372 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.9062. Min Act: -0.1700
Data Index: 849383 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.9062. Min Act: -0.1700
Data Index: 5357825 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.9062. Min Act: -0.1700
Data Index: 4683536 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.8749. Min Act: -0.1700
Data Index: 846363 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.8749. Min Act: -0.1700
Data Index: 6701226 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.8437. Min Act: -0.1700
Data Index: 3748124 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0624. Min Range: -5.0624
Max Act: 4.8437. Min Act: -0.1699
Data Index: 5467371 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19