Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1409 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.6444. Min Act: -0.1700
Data Index: 6620104 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.6444. Min Act: -0.1700
Data Index: 6373789 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.5819. Min Act: -0.1700
Data Index: 814992 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.6131. Min Act: -0.1700
Data Index: 172513 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.6131. Min Act: -0.1700
Data Index: 518285 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.6131. Min Act: -0.1700
Data Index: 68821 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.6131. Min Act: -0.1700
Data Index: 4167462 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.5819. Min Act: -0.1700
Data Index: 8121761 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.5506. Min Act: -0.1700
Data Index: 4167458 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.5506. Min Act: -0.1700
Data Index: 2964657 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.5506. Min Act: -0.1700
Data Index: 3225194 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.5506. Min Act: -0.1700
Data Index: 4167457 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4881. Min Act: -0.1700
Data Index: 4392740 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.5194. Min Act: -0.1700
Data Index: 6450144 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.5194. Min Act: -0.1700
Data Index: 3386984 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.5194. Min Act: -0.1700
Data Index: 814993 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.5194. Min Act: -0.1700
Data Index: 2504294 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.5194. Min Act: -0.1700
Data Index: 4167463 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4881. Min Act: -0.1700
Data Index: 6620100 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4881. Min Act: -0.1700
Data Index: 5848522 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19