Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2990 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0371. Min Range: -4.0371
Max Act: 4.0371. Min Act: -0.1700
Data Index: 6243025 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0371. Min Range: -4.0371
Max Act: 4.0058. Min Act: -0.1700
Data Index: 8026908 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.9433. Min Act: -0.1700
Data Index: 915890 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.9433. Min Act: -0.1700
Data Index: 6352643 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.8495. Min Act: -0.1700
Data Index: 2837075 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.8495. Min Act: -0.1700
Data Index: 2055890 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.8026. Min Act: -0.1700
Data Index: 6730358 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.8026. Min Act: -0.1700
Data Index: 2859247 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.8026. Min Act: -0.1700
Data Index: 5608445 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.7713. Min Act: -0.1700
Data Index: 1348993 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.7557. Min Act: -0.1700
Data Index: 4018680 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.7557. Min Act: -0.1700
Data Index: 5843677 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.7400. Min Act: -0.1700
Data Index: 4728882 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.7244. Min Act: -0.1700
Data Index: 2586181 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.7244. Min Act: -0.1700
Data Index: 137043 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.7244. Min Act: -0.1700
Data Index: 6988584 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.7088. Min Act: -0.1700
Data Index: 3498044 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.7088. Min Act: -0.1700
Data Index: 1177956 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.7088. Min Act: -0.1700
Data Index: 3144482 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0371. Min Range: -4.0371
Max Act: 3.7244. Min Act: -0.1700
Data Index: 996817 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19