Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2992 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.1341. Min Act: -0.1700
Data Index: 5639894 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.1174. Min Act: -0.1700
Data Index: 3763374 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.1174. Min Act: -0.1700
Data Index: 8407278 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.1174. Min Act: -0.1700
Data Index: 152622 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0839. Min Act: -0.1700
Data Index: 939934 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0839. Min Act: -0.1700
Data Index: 6114632 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.1006. Min Act: -0.1700
Data Index: 5688785 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0503. Min Act: -0.1700
Data Index: 2358740 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0671. Min Act: -0.1700
Data Index: 2785296 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0671. Min Act: -0.1700
Data Index: 4878517 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0671. Min Act: -0.1700
Data Index: 2016213 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0503. Min Act: -0.1700
Data Index: 3836242 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0671. Min Act: -0.1700
Data Index: 5576536 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0503. Min Act: -0.1700
Data Index: 2738875 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0503. Min Act: -0.1700
Data Index: 6829405 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0166. Min Act: -0.1700
Data Index: 4015653 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0166. Min Act: -0.1700
Data Index: 3763380 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0335. Min Act: -0.1700
Data Index: 3479134 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0335. Min Act: -0.1699
Data Index: 5856277 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0166. Min Act: -0.1700
Data Index: 3868116 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19