Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3016 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.6445. Min Act: -0.1700
Data Index: 635319 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.5820. Min Act: -0.1700
Data Index: 2060022 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.5195. Min Act: -0.1700
Data Index: 6308346 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.4570. Min Act: -0.1700
Data Index: 7863201 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.4570. Min Act: -0.1700
Data Index: 875431 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.4257. Min Act: -0.1700
Data Index: 5962550 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.3320. Min Act: -0.1700
Data Index: 4486305 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.3007. Min Act: -0.1700
Data Index: 7349818 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.3007. Min Act: -0.1700
Data Index: 3852308 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.2694. Min Act: -0.1700
Data Index: 7182912 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.2382. Min Act: -0.1700
Data Index: 5652833 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.2069. Min Act: -0.1700
Data Index: 6618166 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.2069. Min Act: -0.1700
Data Index: 5641051 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.2069. Min Act: -0.1700
Data Index: 5277708 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.1757. Min Act: -0.1700
Data Index: 5779882 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.1757. Min Act: -0.1700
Data Index: 7460629 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.1757. Min Act: -0.1700
Data Index: 3540110 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.1757. Min Act: -0.1700
Data Index: 4486306 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.1444. Min Act: -0.1700
Data Index: 5778917 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.1444. Min Act: -0.1700
Data Index: 7201319 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19