Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3460 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3513. Min Range: -4.3513
Max Act: 4.3513. Min Act: -0.1700
Data Index: 7738334 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3513. Min Range: -4.3513
Max Act: 4.1638. Min Act: -0.1700
Data Index: 8539780 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3513. Min Range: -4.3513
Max Act: 4.1325. Min Act: -0.1700
Data Index: 6179085 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3513. Min Range: -4.3513
Max Act: 4.1013. Min Act: -0.1700
Data Index: 2831504 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3513. Min Range: -4.3513
Max Act: 4.1013. Min Act: -0.1700
Data Index: 6407969 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3513. Min Range: -4.3513
Max Act: 4.1325. Min Act: -0.1700
Data Index: 350437 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3513. Min Range: -4.3513
Max Act: 4.1013. Min Act: -0.1700
Data Index: 3762968 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3513. Min Range: -4.3513
Max Act: 4.0700. Min Act: -0.1700
Data Index: 2241726 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3513. Min Range: -4.3513
Max Act: 4.0388. Min Act: -0.1700
Data Index: 34141 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3513. Min Range: -4.3513
Max Act: 4.0388. Min Act: -0.1700
Data Index: 7004198 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3513. Min Range: -4.3513
Max Act: 4.0388. Min Act: -0.1700
Data Index: 1622203 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3513. Min Range: -4.3513
Max Act: 4.0388. Min Act: -0.1700
Data Index: 5650639 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3513. Min Range: -4.3513
Max Act: 4.0075. Min Act: -0.1700
Data Index: 1458189 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3513. Min Range: -4.3513
Max Act: 4.0075. Min Act: -0.1700
Data Index: 2051449 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3513. Min Range: -4.3513
Max Act: 4.0075. Min Act: -0.1700
Data Index: 4164565 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3513. Min Range: -4.3513
Max Act: 3.9450. Min Act: -0.1700
Data Index: 6438467 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3513. Min Range: -4.3513
Max Act: 3.9450. Min Act: -0.1700
Data Index: 65038 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3513. Min Range: -4.3513
Max Act: 3.9762. Min Act: -0.1700
Data Index: 966348 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3513. Min Range: -4.3513
Max Act: 3.9762. Min Act: -0.1700
Data Index: 3281791 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3513. Min Range: -4.3513
Max Act: 3.9762. Min Act: -0.1700
Data Index: 516975 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19