Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 619 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0004. Min Range: -5.0004
Max Act: 5.0004. Min Act: -0.1700
Data Index: 5490610 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.9379. Min Act: -0.1700
Data Index: 3393750 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.9066. Min Act: -0.1700
Data Index: 7522259 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.9066. Min Act: -0.1700
Data Index: 3900643 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.8754. Min Act: -0.1700
Data Index: 6771217 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.8754. Min Act: -0.1700
Data Index: 2722307 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.7816. Min Act: -0.1700
Data Index: 7841120 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.7816. Min Act: -0.1700
Data Index: 8409602 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.7504. Min Act: -0.1700
Data Index: 7870303 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.7191. Min Act: -0.1700
Data Index: 2958762 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.7191. Min Act: -0.1700
Data Index: 196287 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.7191. Min Act: -0.1700
Data Index: 1485580 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.7191. Min Act: -0.1700
Data Index: 8471506 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.7191. Min Act: -0.1700
Data Index: 3443222 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.6879. Min Act: -0.1700
Data Index: 6869115 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.6879. Min Act: -0.1700
Data Index: 5801550 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.6879. Min Act: -0.1700
Data Index: 5914582 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.6879. Min Act: -0.1700
Data Index: 5988450 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.6566. Min Act: -0.1700
Data Index: 2118231 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0004. Min Range: -5.0004
Max Act: 4.6566. Min Act: -0.1700
Data Index: 5983768 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19