Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5877 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4199. Min Range: -6.4199
Max Act: 6.4199. Min Act: -0.1700
Data Index: 841039 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4199. Min Range: -6.4199
Max Act: 6.3886. Min Act: -0.1700
Data Index: 5487129 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4199. Min Range: -6.4199
Max Act: 6.2011. Min Act: -0.1700
Data Index: 5487125 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4199. Min Range: -6.4199
Max Act: 6.0761. Min Act: -0.1700
Data Index: 4542359 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4199. Min Range: -6.4199
Max Act: 6.0449. Min Act: -0.1700
Data Index: 4579000 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4199. Min Range: -6.4199
Max Act: 6.0136. Min Act: -0.1700
Data Index: 4401424 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4199. Min Range: -6.4199
Max Act: 5.9824. Min Act: -0.1700
Data Index: 2639822 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4199. Min Range: -6.4199
Max Act: 5.9511. Min Act: -0.1700
Data Index: 5106988 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4199. Min Range: -6.4199
Max Act: 5.9199. Min Act: -0.1700
Data Index: 2257003 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4199. Min Range: -6.4199
Max Act: 5.8886. Min Act: -0.1700
Data Index: 1831100 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4199. Min Range: -6.4199
Max Act: 5.8574. Min Act: -0.1700
Data Index: 3159203 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4199. Min Range: -6.4199
Max Act: 5.8261. Min Act: -0.1700
Data Index: 5723964 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4199. Min Range: -6.4199
Max Act: 5.8261. Min Act: -0.1700
Data Index: 5844993 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4199. Min Range: -6.4199
Max Act: 5.8574. Min Act: -0.1700
Data Index: 7917680 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4199. Min Range: -6.4199
Max Act: 5.8261. Min Act: -0.1700
Data Index: 4985408 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4199. Min Range: -6.4199
Max Act: 5.8574. Min Act: -0.1700
Data Index: 8647662 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4199. Min Range: -6.4199
Max Act: 5.8261. Min Act: -0.1700
Data Index: 6327214 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4199. Min Range: -6.4199
Max Act: 5.8261. Min Act: -0.1700
Data Index: 7017119 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4199. Min Range: -6.4199
Max Act: 5.7949. Min Act: -0.1700
Data Index: 7647502 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4199. Min Range: -6.4199
Max Act: 5.7949. Min Act: -0.1700
Data Index: 4989203 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19