Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4764 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0645. Min Range: -5.0645
Max Act: 5.0645. Min Act: -0.1700
Data Index: 6696811 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.9395. Min Act: -0.1700
Data Index: 7443979 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.9083. Min Act: -0.1700
Data Index: 7955199 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.8458. Min Act: -0.1700
Data Index: 1259205 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.8145. Min Act: -0.1700
Data Index: 6614863 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.7833. Min Act: -0.1700
Data Index: 3930106 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.7833. Min Act: -0.1700
Data Index: 1259195 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.7833. Min Act: -0.1700
Data Index: 5496026 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.7833. Min Act: -0.1700
Data Index: 1259213 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.7520. Min Act: -0.1700
Data Index: 7955224 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.7520. Min Act: -0.1700
Data Index: 6696815 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.7208. Min Act: -0.1700
Data Index: 7955188 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.7208. Min Act: -0.1700
Data Index: 3484543 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.7520. Min Act: -0.1700
Data Index: 1259222 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.7208. Min Act: -0.1700
Data Index: 1969899 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.6583. Min Act: -0.1700
Data Index: 3484532 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.6895. Min Act: -0.1700
Data Index: 6975241 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.6895. Min Act: -0.1700
Data Index: 5293294 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.7208. Min Act: -0.1700
Data Index: 1216294 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0645. Min Range: -5.0645
Max Act: 4.6895. Min Act: -0.1700
Data Index: 2538798 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19