Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5516 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.9777. Min Act: -0.1700
Data Index: 5102662 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.8214. Min Act: -0.1700
Data Index: 430012 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.8214. Min Act: -0.1700
Data Index: 6296038 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.8214. Min Act: -0.1700
Data Index: 2784465 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.7589. Min Act: -0.1700
Data Index: 7739310 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.7277. Min Act: -0.1700
Data Index: 803757 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.6964. Min Act: -0.1700
Data Index: 7219689 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.6964. Min Act: -0.1700
Data Index: 4000950 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.6964. Min Act: -0.1700
Data Index: 7453929 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.6652. Min Act: -0.1700
Data Index: 5700562 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.6339. Min Act: -0.1700
Data Index: 6393361 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.6339. Min Act: -0.1700
Data Index: 6551811 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.6339. Min Act: -0.1700
Data Index: 6710670 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.6027. Min Act: -0.1700
Data Index: 8125166 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.6027. Min Act: -0.1700
Data Index: 4769983 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.6027. Min Act: -0.1700
Data Index: 2369308 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.6339. Min Act: -0.1700
Data Index: 1296983 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.6027. Min Act: -0.1700
Data Index: 1269635 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.6027. Min Act: -0.1700
Data Index: 3287783 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9777. Min Range: -6.9777
Max Act: 6.6027. Min Act: -0.1700
Data Index: 2142496 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19