Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1958 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.6249. Min Act: -0.1700
Data Index: 7601117 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.5624. Min Act: -0.1700
Data Index: 3489717 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.4999. Min Act: -0.1700
Data Index: 491412 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.4687. Min Act: -0.1700
Data Index: 6481292 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.4062. Min Act: -0.1700
Data Index: 1745166 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.3749. Min Act: -0.1700
Data Index: 807660 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.3749. Min Act: -0.1700
Data Index: 6521265 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.3749. Min Act: -0.1700
Data Index: 6923696 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.3749. Min Act: -0.1700
Data Index: 6723889 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.3437. Min Act: -0.1700
Data Index: 3489716 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.3124. Min Act: -0.1700
Data Index: 4908319 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.3437. Min Act: -0.1700
Data Index: 8155410 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.3124. Min Act: -0.1700
Data Index: 4506403 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.3437. Min Act: -0.1700
Data Index: 5865389 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.2812. Min Act: -0.1700
Data Index: 844379 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.2812. Min Act: -0.1700
Data Index: 4263169 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.2812. Min Act: -0.1700
Data Index: 1511271 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.2812. Min Act: -0.1700
Data Index: 1758328 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.2812. Min Act: -0.1700
Data Index: 8292693 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6249. Min Range: -4.6249
Max Act: 4.2499. Min Act: -0.1700
Data Index: 663040 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19