Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 339 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4622. Min Range: -5.4622
Max Act: 5.4622. Min Act: -0.1700
Data Index: 1804506 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4622. Min Range: -5.4622
Max Act: 5.4622. Min Act: -0.1700
Data Index: 7842865 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4622. Min Range: -5.4622
Max Act: 5.3060. Min Act: -0.1700
Data Index: 3597251 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4622. Min Range: -5.4622
Max Act: 5.2122. Min Act: -0.1700
Data Index: 4147358 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4622. Min Range: -5.4622
Max Act: 5.0247. Min Act: -0.1700
Data Index: 8712476 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4622. Min Range: -5.4622
Max Act: 5.1810. Min Act: -0.1700
Data Index: 4038458 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4622. Min Range: -5.4622
Max Act: 5.0872. Min Act: -0.1699
Data Index: 6916934 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4622. Min Range: -5.4622
Max Act: 5.0560. Min Act: -0.1700
Data Index: 7300270 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4622. Min Range: -5.4622
Max Act: 5.1185. Min Act: -0.1699
Data Index: 7683481 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4622. Min Range: -5.4622
Max Act: 5.0872. Min Act: -0.1700
Data Index: 2176762 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4622. Min Range: -5.4622
Max Act: 5.1497. Min Act: -0.1700
Data Index: 3355316 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4622. Min Range: -5.4622
Max Act: 4.9935. Min Act: -0.1700
Data Index: 1202432 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4622. Min Range: -5.4622
Max Act: 5.0247. Min Act: -0.1700
Data Index: 2476780 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4622. Min Range: -5.4622
Max Act: 5.0560. Min Act: -0.1700
Data Index: 6792235 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4622. Min Range: -5.4622
Max Act: 5.0872. Min Act: -0.1700
Data Index: 7265135 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4622. Min Range: -5.4622
Max Act: 5.0247. Min Act: -0.1700
Data Index: 3253537 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4622. Min Range: -5.4622
Max Act: 4.9310. Min Act: -0.1700
Data Index: 1402248 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4622. Min Range: -5.4622
Max Act: 4.9935. Min Act: -0.1700
Data Index: 2771721 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4622. Min Range: -5.4622
Max Act: 5.0560. Min Act: -0.1700
Data Index: 6200908 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4622. Min Range: -5.4622
Max Act: 4.9622. Min Act: -0.1700
Data Index: 6556005 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19