Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.6667. Min Act: -0.1700
Data Index: 1301750 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.4167. Min Act: -0.1700
Data Index: 3829496 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.4167. Min Act: -0.1700
Data Index: 5195188 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.3542. Min Act: -0.1700
Data Index: 4689707 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.3230. Min Act: -0.1700
Data Index: 8390360 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.3542. Min Act: -0.1700
Data Index: 5733087 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.2917. Min Act: -0.1700
Data Index: 3733417 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.2917. Min Act: -0.1700
Data Index: 2245897 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.3230. Min Act: -0.1700
Data Index: 7458119 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.2605. Min Act: -0.1700
Data Index: 7623192 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.2605. Min Act: -0.1700
Data Index: 4728011 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.2292. Min Act: -0.1700
Data Index: 2871905 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.2292. Min Act: -0.1700
Data Index: 6387837 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.2605. Min Act: -0.1700
Data Index: 3971769 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.1980. Min Act: -0.1700
Data Index: 7969296 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.1667. Min Act: -0.1700
Data Index: 8326239 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.1355. Min Act: -0.1700
Data Index: 1615766 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.1667. Min Act: -0.1700
Data Index: 7839210 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.1667. Min Act: -0.1700
Data Index: 142363 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6667. Min Range: -6.6667
Max Act: 6.1667. Min Act: -0.1700
Data Index: 6957708 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19