Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 345 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.4265. Min Act: -0.1700
Data Index: 5486885 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.3795. Min Act: -0.1700
Data Index: 5539027 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.3481. Min Act: -0.1700
Data Index: 710116 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.3324. Min Act: -0.1700
Data Index: 914739 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.3167. Min Act: -0.1700
Data Index: 8302625 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.3481. Min Act: -0.1700
Data Index: 326284 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.3324. Min Act: -0.1700
Data Index: 901248 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.3010. Min Act: -0.1700
Data Index: 8116491 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.2696. Min Act: -0.1700
Data Index: 5059651 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.2696. Min Act: -0.1700
Data Index: 362472 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.2696. Min Act: -0.1700
Data Index: 2637260 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.2853. Min Act: -0.1700
Data Index: 8519039 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.2539. Min Act: -0.1700
Data Index: 3435873 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.2382. Min Act: -0.1700
Data Index: 2041587 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.2068. Min Act: -0.1700
Data Index: 1804803 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.2382. Min Act: -0.1700
Data Index: 5159546 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.2068. Min Act: -0.1700
Data Index: 3361856 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.2225. Min Act: -0.1700
Data Index: 6137047 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.2068. Min Act: -0.1700
Data Index: 4572896 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4265. Min Range: -3.4265
Max Act: 3.2225. Min Act: -0.1700
Data Index: 4368316 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19