Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1105 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.9587. Min Act: -0.1700
Data Index: 3486914 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.8650. Min Act: -0.1700
Data Index: 4296853 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.8337. Min Act: -0.1700
Data Index: 2888420 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.7712. Min Act: -0.1700
Data Index: 6455874 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.6150. Min Act: -0.1700
Data Index: 6904283 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.5525. Min Act: -0.1700
Data Index: 3649936 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.5837. Min Act: -0.1700
Data Index: 6881597 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.5525. Min Act: -0.1700
Data Index: 1318416 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.5212. Min Act: -0.1700
Data Index: 1245384 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.5212. Min Act: -0.1700
Data Index: 1615356 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.5525. Min Act: -0.1700
Data Index: 7864092 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.4900. Min Act: -0.1700
Data Index: 4919387 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.4900. Min Act: -0.1700
Data Index: 758371 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.4587. Min Act: -0.1700
Data Index: 6508994 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.4900. Min Act: -0.1700
Data Index: 173004 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.4900. Min Act: -0.1700
Data Index: 5101159 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.3962. Min Act: -0.1700
Data Index: 8653669 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.3962. Min Act: -0.1700
Data Index: 6481272 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.3962. Min Act: -0.1700
Data Index: 1362640 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9587. Min Range: -6.9587
Max Act: 6.3650. Min Act: -0.1700
Data Index: 1001351 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19