Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1646 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.5964. Min Act: -0.1700
Data Index: 2505870 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.5652. Min Act: -0.1700
Data Index: 4017309 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.4089. Min Act: -0.1700
Data Index: 4298490 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.4089. Min Act: -0.1700
Data Index: 472679 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.3777. Min Act: -0.1700
Data Index: 4273807 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.3777. Min Act: -0.1700
Data Index: 2975295 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.3464. Min Act: -0.1700
Data Index: 492159 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.3152. Min Act: -0.1700
Data Index: 1707088 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.2839. Min Act: -0.1700
Data Index: 4863759 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.2527. Min Act: -0.1700
Data Index: 7911815 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.1902. Min Act: -0.1700
Data Index: 8160673 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.1589. Min Act: -0.1700
Data Index: 3527814 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.1589. Min Act: -0.1700
Data Index: 6900849 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.1277. Min Act: -0.1700
Data Index: 8632562 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.1277. Min Act: -0.1700
Data Index: 254494 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.0964. Min Act: -0.1700
Data Index: 6865449 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.0964. Min Act: -0.1700
Data Index: 3185207 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.0964. Min Act: -0.1700
Data Index: 5622589 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.0964. Min Act: -0.1700
Data Index: 4369059 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5964. Min Range: -6.5964
Max Act: 6.0652. Min Act: -0.1700
Data Index: 5037687 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19