Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1157 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1893. Min Range: -4.1893
Max Act: 4.1893. Min Act: -0.1700
Data Index: 572945 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1893. Min Range: -4.1893
Max Act: 4.1893. Min Act: -0.1700
Data Index: 4826323 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1893. Min Range: -4.1893
Max Act: 4.1581. Min Act: -0.1700
Data Index: 4148007 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1893. Min Range: -4.1893
Max Act: 4.1581. Min Act: -0.1700
Data Index: 1856958 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1893. Min Range: -4.1893
Max Act: 4.1268. Min Act: -0.1700
Data Index: 572936 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1893. Min Range: -4.1893
Max Act: 4.0956. Min Act: -0.1700
Data Index: 6651299 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1893. Min Range: -4.1893
Max Act: 4.0643. Min Act: -0.1700
Data Index: 8315877 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1893. Min Range: -4.1893
Max Act: 4.0643. Min Act: -0.1700
Data Index: 1807715 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1893. Min Range: -4.1893
Max Act: 4.0331. Min Act: -0.1700
Data Index: 5514013 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1893. Min Range: -4.1893
Max Act: 4.0018. Min Act: -0.1700
Data Index: 3529034 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1893. Min Range: -4.1893
Max Act: 3.9393. Min Act: -0.1700
Data Index: 7209829 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1893. Min Range: -4.1893
Max Act: 3.9705. Min Act: -0.1700
Data Index: 3706618 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1893. Min Range: -4.1893
Max Act: 3.9705. Min Act: -0.1700
Data Index: 428238 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1893. Min Range: -4.1893
Max Act: 4.0018. Min Act: -0.1700
Data Index: 4625229 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1893. Min Range: -4.1893
Max Act: 3.9393. Min Act: -0.1700
Data Index: 5392366 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1893. Min Range: -4.1893
Max Act: 3.9393. Min Act: -0.1700
Data Index: 939644 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1893. Min Range: -4.1893
Max Act: 3.9393. Min Act: -0.1700
Data Index: 4900470 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1893. Min Range: -4.1893
Max Act: 3.9393. Min Act: -0.1700
Data Index: 2449567 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1893. Min Range: -4.1893
Max Act: 3.9080. Min Act: -0.1700
Data Index: 3776555 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1893. Min Range: -4.1893
Max Act: 3.9080. Min Act: -0.1700
Data Index: 466027 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19