Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3803 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.9777. Min Act: -0.1700
Data Index: 4428939 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.9777. Min Act: -0.1700
Data Index: 154811 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.9464. Min Act: -0.1700
Data Index: 1338469 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.9152. Min Act: -0.1700
Data Index: 8162526 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.9152. Min Act: -0.1700
Data Index: 3329684 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.8527. Min Act: -0.1700
Data Index: 7128055 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.8839. Min Act: -0.1700
Data Index: 7589997 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.8527. Min Act: -0.1700
Data Index: 1446217 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.8527. Min Act: -0.1700
Data Index: 5656242 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.8214. Min Act: -0.1700
Data Index: 414793 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.7902. Min Act: -0.1700
Data Index: 3639366 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.7902. Min Act: -0.1700
Data Index: 3501156 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.7902. Min Act: -0.1700
Data Index: 726707 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.7589. Min Act: -0.1700
Data Index: 3135085 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.7589. Min Act: -0.1700
Data Index: 1062449 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.6964. Min Act: -0.1700
Data Index: 6461858 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.7277. Min Act: -0.1700
Data Index: 7117057 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.7277. Min Act: -0.1700
Data Index: 6067146 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.7277. Min Act: -0.1700
Data Index: 6002239 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9777. Min Range: -4.9777
Max Act: 4.6964. Min Act: -0.1700
Data Index: 5779996 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19