Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.6276. Min Range: -9.6276
Max Act: 9.6276. Min Act: -0.1700
Data Index: 5479198 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6276. Min Range: -9.6276
Max Act: 9.5026. Min Act: -0.1700
Data Index: 3307421 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6276. Min Range: -9.6276
Max Act: 9.5026. Min Act: -0.1700
Data Index: 1270885 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6276. Min Range: -9.6276
Max Act: 9.3776. Min Act: -0.1700
Data Index: 3001883 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6276. Min Range: -9.6276
Max Act: 9.2526. Min Act: -0.1700
Data Index: 7961600 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6276. Min Range: -9.6276
Max Act: 9.0651. Min Act: -0.1700
Data Index: 1411917 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6276. Min Range: -9.6276
Max Act: 8.8776. Min Act: -0.1700
Data Index: 2255019 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6276. Min Range: -9.6276
Max Act: 8.8776. Min Act: -0.1700
Data Index: 7535938 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6276. Min Range: -9.6276
Max Act: 8.8151. Min Act: -0.1700
Data Index: 4998801 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6276. Min Range: -9.6276
Max Act: 8.8151. Min Act: -0.1700
Data Index: 1801356 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6276. Min Range: -9.6276
Max Act: 8.8151. Min Act: -0.1700
Data Index: 7789721 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6276. Min Range: -9.6276
Max Act: 8.7526. Min Act: -0.1700
Data Index: 371722 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6276. Min Range: -9.6276
Max Act: 8.7526. Min Act: -0.1700
Data Index: 1801355 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6276. Min Range: -9.6276
Max Act: 8.6901. Min Act: -0.1700
Data Index: 913068 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6276. Min Range: -9.6276
Max Act: 8.6901. Min Act: -0.1700
Data Index: 7224565 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6276. Min Range: -9.6276
Max Act: 8.6901. Min Act: -0.1700
Data Index: 1999508 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6276. Min Range: -9.6276
Max Act: 8.6901. Min Act: -0.1700
Data Index: 5503634 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6276. Min Range: -9.6276
Max Act: 8.6901. Min Act: -0.1700
Data Index: 2255020 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6276. Min Range: -9.6276
Max Act: 8.6276. Min Act: -0.1700
Data Index: 1801353 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6276. Min Range: -9.6276
Max Act: 8.6276. Min Act: -0.1700
Data Index: 3060381 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19