Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3231 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3134. Min Range: -6.3134
Max Act: 6.3134. Min Act: -0.1700
Data Index: 6413761 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3134. Min Range: -6.3134
Max Act: 6.0322. Min Act: -0.1700
Data Index: 6219557 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.9384. Min Act: -0.1700
Data Index: 732597 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.9697. Min Act: -0.1700
Data Index: 4185596 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.9697. Min Act: -0.1700
Data Index: 6647980 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.9072. Min Act: -0.1700
Data Index: 7664498 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.9072. Min Act: -0.1700
Data Index: 4756900 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.8759. Min Act: -0.1699
Data Index: 7565246 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.7822. Min Act: -0.1700
Data Index: 8392847 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.7509. Min Act: -0.1700
Data Index: 1449355 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.7197. Min Act: -0.1700
Data Index: 5962280 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.7197. Min Act: -0.1700
Data Index: 18406 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.7197. Min Act: -0.1700
Data Index: 8242618 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.7197. Min Act: -0.1700
Data Index: 7619521 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.7197. Min Act: -0.1700
Data Index: 191302 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.6884. Min Act: -0.1700
Data Index: 5075357 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.6884. Min Act: -0.1700
Data Index: 3136060 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.6572. Min Act: -0.1700
Data Index: 3895445 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.6259. Min Act: -0.1700
Data Index: 2054043 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3134. Min Range: -6.3134
Max Act: 5.6259. Min Act: -0.1700
Data Index: 5501356 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19