Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2180 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1452. Min Range: -7.1452
Max Act: 7.1452. Min Act: -0.1700
Data Index: 4276159 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1452. Min Range: -7.1452
Max Act: 7.0202. Min Act: -0.1700
Data Index: 3312936 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.9264. Min Act: -0.1700
Data Index: 8380031 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.9264. Min Act: -0.1700
Data Index: 2662528 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.8952. Min Act: -0.1700
Data Index: 8423923 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.8327. Min Act: -0.1700
Data Index: 4037205 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.8327. Min Act: -0.1700
Data Index: 7372863 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.8327. Min Act: -0.1700
Data Index: 4000352 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.7702. Min Act: -0.1700
Data Index: 3820131 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.8014. Min Act: -0.1700
Data Index: 4926651 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.7389. Min Act: -0.1700
Data Index: 6127199 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.7389. Min Act: -0.1700
Data Index: 3215973 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.6764. Min Act: -0.1700
Data Index: 1079099 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.7077. Min Act: -0.1700
Data Index: 7771513 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.7077. Min Act: -0.1700
Data Index: 7491692 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.6764. Min Act: -0.1700
Data Index: 2914471 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.7077. Min Act: -0.1700
Data Index: 1514632 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.7389. Min Act: -0.1700
Data Index: 1747414 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.7077. Min Act: -0.1700
Data Index: 3260141 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1452. Min Range: -7.1452
Max Act: 6.6764. Min Act: -0.1700
Data Index: 518233 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19