Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1340 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.6276. Min Act: -0.1700
Data Index: 5344401 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.4661. Min Act: -0.1700
Data Index: 5333664 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.4173. Min Act: -0.1700
Data Index: 7915571 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.4336. Min Act: -0.1700
Data Index: 2056562 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.4498. Min Act: -0.1700
Data Index: 4877581 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.4336. Min Act: -0.1700
Data Index: 3213223 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.4173. Min Act: -0.1700
Data Index: 6354878 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.4173. Min Act: -0.1700
Data Index: 2014667 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.4010. Min Act: -0.1700
Data Index: 346605 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.4010. Min Act: -0.1700
Data Index: 4297165 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.3846. Min Act: -0.1700
Data Index: 8331091 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.3846. Min Act: -0.1700
Data Index: 8394183 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.3846. Min Act: -0.1700
Data Index: 6926503 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.4010. Min Act: -0.1700
Data Index: 1253321 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.3846. Min Act: -0.1700
Data Index: 1730622 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.4010. Min Act: -0.1700
Data Index: 5031614 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.3846. Min Act: -0.1700
Data Index: 3111412 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.3683. Min Act: -0.1700
Data Index: 1394351 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.3519. Min Act: -0.1700
Data Index: 5555404 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6276. Min Range: -2.6276
Max Act: 2.3519. Min Act: -0.1700
Data Index: 5242076 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19