Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3574 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1863. Min Range: -6.1863
Max Act: 6.1863. Min Act: -0.1700
Data Index: 7166415 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.7801. Min Act: -0.1700
Data Index: 5781226 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.7488. Min Act: -0.1700
Data Index: 2339960 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.7488. Min Act: -0.1700
Data Index: 8191178 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.7488. Min Act: -0.1700
Data Index: 591534 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.5926. Min Act: -0.1700
Data Index: 754297 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.5613. Min Act: -0.1700
Data Index: 7769371 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.6238. Min Act: -0.1700
Data Index: 6704482 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.5613. Min Act: -0.1700
Data Index: 3148928 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.5613. Min Act: -0.1700
Data Index: 341959 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.5301. Min Act: -0.1700
Data Index: 3874031 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.5301. Min Act: -0.1700
Data Index: 4371787 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.4988. Min Act: -0.1700
Data Index: 8764816 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.4676. Min Act: -0.1700
Data Index: 2384613 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.5301. Min Act: -0.1700
Data Index: 1531195 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.4988. Min Act: -0.1700
Data Index: 3104580 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.4676. Min Act: -0.1700
Data Index: 5058219 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.4363. Min Act: -0.1700
Data Index: 8644038 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.4676. Min Act: -0.1700
Data Index: 4284947 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1863. Min Range: -6.1863
Max Act: 5.4051. Min Act: -0.1700
Data Index: 4215492 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19