Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2253 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.3749. Min Act: -0.1700
Data Index: 8780652 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.2764. Min Act: -0.1700
Data Index: 4857949 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.2434. Min Act: -0.1699
Data Index: 1258905 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.2268. Min Act: -0.1699
Data Index: 736836 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.2434. Min Act: -0.1700
Data Index: 7724018 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.2434. Min Act: -0.1700
Data Index: 3033186 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.2434. Min Act: -0.1700
Data Index: 6805483 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.2434. Min Act: -0.1700
Data Index: 7759625 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.2103. Min Act: -0.1700
Data Index: 7266478 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.2103. Min Act: -0.1700
Data Index: 3356265 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.2103. Min Act: -0.1700
Data Index: 7347146 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.2103. Min Act: -0.1700
Data Index: 7926243 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.2103. Min Act: -0.1700
Data Index: 4166526 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.2103. Min Act: -0.1699
Data Index: 2520085 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.1771. Min Act: -0.1700
Data Index: 1707510 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.1937. Min Act: -0.1698
Data Index: 3907638 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.1937. Min Act: -0.1700
Data Index: 533292 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.1937. Min Act: -0.1700
Data Index: 998751 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.1937. Min Act: -0.1700
Data Index: 5638717 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3749. Min Range: -2.3749
Max Act: 2.1771. Min Act: -0.1700
Data Index: 4852735 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19