Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2882 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.9572. Min Act: -0.1700
Data Index: 5911201 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.9399. Min Act: -0.1700
Data Index: 4415335 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.9485. Min Act: -0.1700
Data Index: 6193014 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.9227. Min Act: -0.1700
Data Index: 4687345 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.9142. Min Act: -0.1700
Data Index: 2574166 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.9056. Min Act: -0.1700
Data Index: 8033188 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.8970. Min Act: -0.1700
Data Index: 8426158 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.9056. Min Act: -0.1700
Data Index: 1270781 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.9056. Min Act: -0.1700
Data Index: 6557581 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.8970. Min Act: -0.1700
Data Index: 3341501 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.8970. Min Act: -0.1700
Data Index: 591429 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.9056. Min Act: -0.1700
Data Index: 3390364 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.8885. Min Act: -0.1700
Data Index: 6852377 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.8885. Min Act: -0.1700
Data Index: 6253994 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.8885. Min Act: -0.1700
Data Index: 6609521 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.8800. Min Act: -0.1700
Data Index: 216030 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.8800. Min Act: -0.1700
Data Index: 6765398 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.8885. Min Act: -0.1700
Data Index: 2446220 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.8800. Min Act: -0.1700
Data Index: 157307 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9572. Min Range: -0.9572
Max Act: 0.8885. Min Act: -0.1700
Data Index: 8388905 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19