Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 894 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.4507. Min Act: -0.1700
Data Index: 2421159 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.2007. Min Act: -0.1700
Data Index: 4345754 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.1695. Min Act: -0.1700
Data Index: 254223 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.1695. Min Act: -0.1700
Data Index: 2726695 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.1070. Min Act: -0.1700
Data Index: 798482 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.1382. Min Act: -0.1700
Data Index: 1426031 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.1070. Min Act: -0.1700
Data Index: 605600 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.1070. Min Act: -0.1700
Data Index: 1099853 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.1070. Min Act: -0.1700
Data Index: 7478670 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.0757. Min Act: -0.1700
Data Index: 3179958 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.0757. Min Act: -0.1700
Data Index: 809308 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.0757. Min Act: -0.1700
Data Index: 6763574 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.1070. Min Act: -0.1700
Data Index: 4399645 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.0445. Min Act: -0.1700
Data Index: 732692 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.0445. Min Act: -0.1700
Data Index: 1346900 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.0445. Min Act: -0.1700
Data Index: 5865629 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.0445. Min Act: -0.1700
Data Index: 7157120 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.0132. Min Act: -0.1700
Data Index: 8702878 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4507. Min Range: -5.4507
Max Act: 5.0132. Min Act: -0.1700
Data Index: 6568449 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4507. Min Range: -5.4507
Max Act: 4.9820. Min Act: -0.1700
Data Index: 6666387 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19