Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1089 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.7249. Min Act: -0.1700
Data Index: 2272287 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.6624. Min Act: -0.1700
Data Index: 529174 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.5374. Min Act: -0.1700
Data Index: 5813901 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.5374. Min Act: -0.1700
Data Index: 4143837 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.4436. Min Act: -0.1700
Data Index: 5177668 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.4436. Min Act: -0.1700
Data Index: 3888704 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.4436. Min Act: -0.1700
Data Index: 5372670 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.3811. Min Act: -0.1700
Data Index: 7500862 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.3499. Min Act: -0.1700
Data Index: 3518450 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.2249. Min Act: -0.1700
Data Index: 2785861 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.1936. Min Act: -0.1700
Data Index: 8419303 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.1623. Min Act: -0.1700
Data Index: 6355625 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.1311. Min Act: -0.1700
Data Index: 1171319 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.1623. Min Act: -0.1700
Data Index: 641779 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.0998. Min Act: -0.1700
Data Index: 5654685 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.0998. Min Act: -0.1700
Data Index: 5284354 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.0686. Min Act: -0.1700
Data Index: 2746064 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.0373. Min Act: -0.1700
Data Index: 5589301 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.0686. Min Act: -0.1700
Data Index: 8375618 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.0686. Min Act: -0.1700
Data Index: 3480379 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19