Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2954 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1154. Min Range: -5.1154
Max Act: 5.1154. Min Act: -0.1700
Data Index: 1567971 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1154. Min Range: -5.1154
Max Act: 5.1154. Min Act: -0.1700
Data Index: 4248077 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1154. Min Range: -5.1154
Max Act: 5.1154. Min Act: -0.1700
Data Index: 3070915 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1154. Min Range: -5.1154
Max Act: 5.0842. Min Act: -0.1700
Data Index: 2978955 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1154. Min Range: -5.1154
Max Act: 5.0842. Min Act: -0.1700
Data Index: 4559591 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1154. Min Range: -5.1154
Max Act: 5.0842. Min Act: -0.1700
Data Index: 2320665 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1154. Min Range: -5.1154
Max Act: 5.0529. Min Act: -0.1700
Data Index: 4559588 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1154. Min Range: -5.1154
Max Act: 5.0529. Min Act: -0.1700
Data Index: 4559586 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1154. Min Range: -5.1154
Max Act: 5.0529. Min Act: -0.1700
Data Index: 1543885 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1154. Min Range: -5.1154
Max Act: 5.0529. Min Act: -0.1700
Data Index: 8494083 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1154. Min Range: -5.1154
Max Act: 5.0217. Min Act: -0.1700
Data Index: 8471693 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1154. Min Range: -5.1154
Max Act: 5.0217. Min Act: -0.1700
Data Index: 4559585 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1154. Min Range: -5.1154
Max Act: 4.9904. Min Act: -0.1700
Data Index: 208581 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1154. Min Range: -5.1154
Max Act: 4.9904. Min Act: -0.1700
Data Index: 2860547 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1154. Min Range: -5.1154
Max Act: 5.0217. Min Act: -0.1700
Data Index: 6934824 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1154. Min Range: -5.1154
Max Act: 4.9904. Min Act: -0.1700
Data Index: 6751558 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1154. Min Range: -5.1154
Max Act: 4.9904. Min Act: -0.1700
Data Index: 5501755 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1154. Min Range: -5.1154
Max Act: 4.9904. Min Act: -0.1700
Data Index: 2189664 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1154. Min Range: -5.1154
Max Act: 4.9279. Min Act: -0.1700
Data Index: 310891 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1154. Min Range: -5.1154
Max Act: 4.9592. Min Act: -0.1700
Data Index: 3507456 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19