Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 395 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.8070. Min Act: -0.1700
Data Index: 2362677 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.7758. Min Act: -0.1700
Data Index: 6510398 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.7758. Min Act: -0.1700
Data Index: 347135 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.7445. Min Act: -0.1700
Data Index: 1248566 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.7133. Min Act: -0.1700
Data Index: 6829002 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.6820. Min Act: -0.1700
Data Index: 8749665 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.6508. Min Act: -0.1700
Data Index: 6906856 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.6508. Min Act: -0.1700
Data Index: 2243865 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.6195. Min Act: -0.1700
Data Index: 8560935 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.6195. Min Act: -0.1700
Data Index: 5657056 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.5883. Min Act: -0.1700
Data Index: 4676783 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.5883. Min Act: -0.1700
Data Index: 3709944 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.5883. Min Act: -0.1700
Data Index: 5100128 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.6195. Min Act: -0.1700
Data Index: 8062049 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.5258. Min Act: -0.1700
Data Index: 719279 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.5570. Min Act: -0.1700
Data Index: 6338412 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.5258. Min Act: -0.1700
Data Index: 4594157 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.4945. Min Act: -0.1700
Data Index: 2296435 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.4320. Min Act: -0.1700
Data Index: 4295661 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8070. Min Range: -5.8070
Max Act: 5.4945. Min Act: -0.1700
Data Index: 4302107 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19