Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3121 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.7585. Min Act: -0.1700
Data Index: 2536014 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.6023. Min Act: -0.1700
Data Index: 2333368 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.5710. Min Act: -0.1700
Data Index: 4418770 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.5398. Min Act: -0.1700
Data Index: 5648868 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.5085. Min Act: -0.1700
Data Index: 3901079 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.5085. Min Act: -0.1700
Data Index: 3800027 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.5085. Min Act: -0.1700
Data Index: 5758083 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.5085. Min Act: -0.1700
Data Index: 5133071 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.4460. Min Act: -0.1700
Data Index: 4979233 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.4773. Min Act: -0.1700
Data Index: 3603517 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.4773. Min Act: -0.1700
Data Index: 5283149 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.4773. Min Act: -0.1700
Data Index: 396281 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.4460. Min Act: -0.1700
Data Index: 1716861 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.4460. Min Act: -0.1700
Data Index: 8687393 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.4460. Min Act: -0.1700
Data Index: 4002496 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.4460. Min Act: -0.1700
Data Index: 8129774 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.4460. Min Act: -0.1700
Data Index: 1825760 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.4460. Min Act: -0.1700
Data Index: 5566535 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.4148. Min Act: -0.1700
Data Index: 3633380 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7585. Min Range: -5.7585
Max Act: 5.4148. Min Act: -0.1700
Data Index: 4356507 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19