Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5635 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.6167. Min Act: -0.1700
Data Index: 4855666 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.4917. Min Act: -0.1700
Data Index: 5285631 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.4292. Min Act: -0.1700
Data Index: 5666896 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.4292. Min Act: -0.1700
Data Index: 6108342 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.4292. Min Act: -0.1700
Data Index: 3364788 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.4292. Min Act: -0.1700
Data Index: 1604959 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.4292. Min Act: -0.1700
Data Index: 7751463 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.3979. Min Act: -0.1700
Data Index: 408210 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.3667. Min Act: -0.1700
Data Index: 5115220 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.3979. Min Act: -0.1700
Data Index: 1986 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.3667. Min Act: -0.1700
Data Index: 2645939 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.3667. Min Act: -0.1700
Data Index: 2300526 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.3041. Min Act: -0.1700
Data Index: 1789830 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.3354. Min Act: -0.1700
Data Index: 2284984 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.3354. Min Act: -0.1700
Data Index: 4816117 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.3354. Min Act: -0.1700
Data Index: 8583008 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.3041. Min Act: -0.1700
Data Index: 3576385 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.2729. Min Act: -0.1700
Data Index: 7170249 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.2729. Min Act: -0.1700
Data Index: 2814832 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6167. Min Range: -4.6167
Max Act: 4.2729. Min Act: -0.1700
Data Index: 5315971 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19