Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3109 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.6019. Min Act: -0.1700
Data Index: 5791512 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.5706. Min Act: -0.1700
Data Index: 4563615 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.5706. Min Act: -0.1700
Data Index: 3887749 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.5394. Min Act: -0.1700
Data Index: 2218105 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.5081. Min Act: -0.1700
Data Index: 5956739 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.4769. Min Act: -0.1700
Data Index: 372433 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.4456. Min Act: -0.1700
Data Index: 8549817 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.4144. Min Act: -0.1700
Data Index: 8182646 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.3831. Min Act: -0.1700
Data Index: 2732943 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.3831. Min Act: -0.1700
Data Index: 8591831 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.3519. Min Act: -0.1700
Data Index: 8424282 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.3831. Min Act: -0.1700
Data Index: 7532535 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.3831. Min Act: -0.1700
Data Index: 7268171 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.3519. Min Act: -0.1700
Data Index: 2230382 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.3519. Min Act: -0.1700
Data Index: 8524169 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.3519. Min Act: -0.1700
Data Index: 7692444 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.3519. Min Act: -0.1700
Data Index: 7952208 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.3519. Min Act: -0.1700
Data Index: 593887 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.2894. Min Act: -0.1700
Data Index: 5228503 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6019. Min Range: -5.6019
Max Act: 5.3206. Min Act: -0.1700
Data Index: 3167688 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19