Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1166 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.5964. Min Act: -0.1700
Data Index: 5693185 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.5339. Min Act: -0.1700
Data Index: 8089758 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.3776. Min Act: -0.1700
Data Index: 539089 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.3464. Min Act: -0.1700
Data Index: 4163878 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.3151. Min Act: -0.1700
Data Index: 3644951 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.2526. Min Act: -0.1700
Data Index: 1325226 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.2214. Min Act: -0.1700
Data Index: 5391494 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.1901. Min Act: -0.1700
Data Index: 4597630 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.1901. Min Act: -0.1700
Data Index: 3794099 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.1276. Min Act: -0.1700
Data Index: 537438 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.1276. Min Act: -0.1700
Data Index: 1105356 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.0964. Min Act: -0.1700
Data Index: 1393277 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.0964. Min Act: -0.1700
Data Index: 4499507 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.0651. Min Act: -0.1700
Data Index: 1801686 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.0651. Min Act: -0.1700
Data Index: 4181960 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.0651. Min Act: -0.1700
Data Index: 4417882 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.0339. Min Act: -0.1700
Data Index: 2391302 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5964. Min Range: -7.5964
Max Act: 7.0651. Min Act: -0.1700
Data Index: 5118471 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5964. Min Range: -7.5964
Max Act: 6.9714. Min Act: -0.1700
Data Index: 22033 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5964. Min Range: -7.5964
Max Act: 6.9714. Min Act: -0.1700
Data Index: 4186391 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19