Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1639 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3294. Min Range: -3.3294
Max Act: 3.3294. Min Act: -0.1700
Data Index: 5032080 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3294. Min Range: -3.3294
Max Act: 3.2195. Min Act: -0.1700
Data Index: 2966966 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3294. Min Range: -3.3294
Max Act: 3.1566. Min Act: -0.1700
Data Index: 2187451 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3294. Min Range: -3.3294
Max Act: 3.1408. Min Act: -0.1700
Data Index: 7941227 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3294. Min Range: -3.3294
Max Act: 3.0778. Min Act: -0.1700
Data Index: 4346878 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3294. Min Range: -3.3294
Max Act: 3.0778. Min Act: -0.1700
Data Index: 5499161 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3294. Min Range: -3.3294
Max Act: 3.0305. Min Act: -0.1700
Data Index: 2042029 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3294. Min Range: -3.3294
Max Act: 3.0147. Min Act: -0.1700
Data Index: 3751184 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3294. Min Range: -3.3294
Max Act: 2.9831. Min Act: -0.1700
Data Index: 5314306 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3294. Min Range: -3.3294
Max Act: 2.9514. Min Act: -0.1700
Data Index: 5539178 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3294. Min Range: -3.3294
Max Act: 2.9514. Min Act: -0.1700
Data Index: 350654 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3294. Min Range: -3.3294
Max Act: 2.9356. Min Act: -0.1700
Data Index: 7584266 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3294. Min Range: -3.3294
Max Act: 2.9356. Min Act: -0.1700
Data Index: 7402519 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3294. Min Range: -3.3294
Max Act: 2.9514. Min Act: -0.1700
Data Index: 1430746 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3294. Min Range: -3.3294
Max Act: 2.9197. Min Act: -0.1700
Data Index: 2740228 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3294. Min Range: -3.3294
Max Act: 2.9197. Min Act: -0.1700
Data Index: 311495 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3294. Min Range: -3.3294
Max Act: 2.9197. Min Act: -0.1700
Data Index: 6875952 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3294. Min Range: -3.3294
Max Act: 2.9197. Min Act: -0.1700
Data Index: 7648449 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3294. Min Range: -3.3294
Max Act: 2.8880. Min Act: -0.1700
Data Index: 2678279 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3294. Min Range: -3.3294
Max Act: 2.9039. Min Act: -0.1700
Data Index: 4471416 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19