Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3046 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0622. Min Range: -4.0622
Max Act: 4.0622. Min Act: -0.1700
Data Index: 7624484 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.9059. Min Act: -0.1700
Data Index: 5187406 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.9372. Min Act: -0.1700
Data Index: 7545451 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.9059. Min Act: -0.1700
Data Index: 1186465 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.8434. Min Act: -0.1700
Data Index: 5125223 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.8746. Min Act: -0.1700
Data Index: 8032860 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.8746. Min Act: -0.1700
Data Index: 6960388 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.8746. Min Act: -0.1700
Data Index: 758724 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.8434. Min Act: -0.1700
Data Index: 2699239 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.8434. Min Act: -0.1700
Data Index: 4135222 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.8434. Min Act: -0.1700
Data Index: 3274906 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.8277. Min Act: -0.1700
Data Index: 3951677 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.8277. Min Act: -0.1700
Data Index: 8524213 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.8434. Min Act: -0.1700
Data Index: 7563757 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.8121. Min Act: -0.1700
Data Index: 2699240 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.8277. Min Act: -0.1700
Data Index: 5099220 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.8121. Min Act: -0.1700
Data Index: 3293450 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.7808. Min Act: -0.1700
Data Index: 7370416 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.7808. Min Act: -0.1700
Data Index: 6853631 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0622. Min Range: -4.0622
Max Act: 3.7965. Min Act: -0.1700
Data Index: 7623886 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19