Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3444 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3922. Min Range: -8.3922
Max Act: 8.3922. Min Act: -0.1700
Data Index: 342163 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3922. Min Range: -8.3922
Max Act: 8.2672. Min Act: -0.1700
Data Index: 7852046 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3922. Min Range: -8.3922
Max Act: 8.2672. Min Act: -0.1700
Data Index: 5736286 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3922. Min Range: -8.3922
Max Act: 8.0797. Min Act: -0.1700
Data Index: 1287024 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3922. Min Range: -8.3922
Max Act: 8.1110. Min Act: -0.1700
Data Index: 4251058 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3922. Min Range: -8.3922
Max Act: 8.1110. Min Act: -0.1700
Data Index: 2166416 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3922. Min Range: -8.3922
Max Act: 8.0172. Min Act: -0.1700
Data Index: 1277053 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3922. Min Range: -8.3922
Max Act: 7.9235. Min Act: -0.1700
Data Index: 1558283 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3922. Min Range: -8.3922
Max Act: 7.9547. Min Act: -0.1700
Data Index: 1632050 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3922. Min Range: -8.3922
Max Act: 7.9235. Min Act: -0.1700
Data Index: 3166837 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3922. Min Range: -8.3922
Max Act: 7.9547. Min Act: -0.1700
Data Index: 3364139 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3922. Min Range: -8.3922
Max Act: 7.9547. Min Act: -0.1700
Data Index: 2744388 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3922. Min Range: -8.3922
Max Act: 7.9235. Min Act: -0.1700
Data Index: 4831958 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3922. Min Range: -8.3922
Max Act: 7.8297. Min Act: -0.1700
Data Index: 6657603 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3922. Min Range: -8.3922
Max Act: 7.9235. Min Act: -0.1700
Data Index: 5459333 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3922. Min Range: -8.3922
Max Act: 7.7672. Min Act: -0.1700
Data Index: 4224340 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3922. Min Range: -8.3922
Max Act: 7.7672. Min Act: -0.1700
Data Index: 4638409 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3922. Min Range: -8.3922
Max Act: 7.8297. Min Act: -0.1700
Data Index: 7254894 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3922. Min Range: -8.3922
Max Act: 7.7360. Min Act: -0.1700
Data Index: 7975169 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3922. Min Range: -8.3922
Max Act: 7.6422. Min Act: -0.1700
Data Index: 4300112 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19