Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3606 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8233. Min Range: -9.8233
Max Act: 9.8233. Min Act: -0.1700
Data Index: 7697040 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8233. Min Range: -9.8233
Max Act: 9.3858. Min Act: -0.1700
Data Index: 784084 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8233. Min Range: -9.8233
Max Act: 9.3233. Min Act: -0.1700
Data Index: 1351324 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8233. Min Range: -9.8233
Max Act: 9.1983. Min Act: -0.1700
Data Index: 1924899 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8233. Min Range: -9.8233
Max Act: 9.1358. Min Act: -0.1700
Data Index: 6216343 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8233. Min Range: -9.8233
Max Act: 9.1358. Min Act: -0.1700
Data Index: 7139470 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8233. Min Range: -9.8233
Max Act: 9.0108. Min Act: -0.1700
Data Index: 2797334 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8233. Min Range: -9.8233
Max Act: 9.0108. Min Act: -0.1700
Data Index: 4123334 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8233. Min Range: -9.8233
Max Act: 8.9483. Min Act: -0.1700
Data Index: 4035933 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8233. Min Range: -9.8233
Max Act: 8.9483. Min Act: -0.1700
Data Index: 1690030 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8233. Min Range: -9.8233
Max Act: 8.8858. Min Act: -0.1700
Data Index: 5321441 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8233. Min Range: -9.8233
Max Act: 8.8858. Min Act: -0.1700
Data Index: 2434485 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8233. Min Range: -9.8233
Max Act: 8.8858. Min Act: -0.1700
Data Index: 514704 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8233. Min Range: -9.8233
Max Act: 8.8233. Min Act: -0.1700
Data Index: 8291283 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8233. Min Range: -9.8233
Max Act: 8.8233. Min Act: -0.1700
Data Index: 8810627 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8233. Min Range: -9.8233
Max Act: 8.8233. Min Act: -0.1700
Data Index: 5215374 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8233. Min Range: -9.8233
Max Act: 8.8233. Min Act: -0.1700
Data Index: 3112694 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8233. Min Range: -9.8233
Max Act: 8.7608. Min Act: -0.1700
Data Index: 7954077 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8233. Min Range: -9.8233
Max Act: 8.7608. Min Act: -0.1700
Data Index: 3727415 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8233. Min Range: -9.8233
Max Act: 8.6983. Min Act: -0.1700
Data Index: 2240412 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19