Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2119 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0881. Min Range: -7.0881
Max Act: 7.0881. Min Act: -0.1700
Data Index: 476634 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0881. Min Range: -7.0881
Max Act: 7.0881. Min Act: -0.1700
Data Index: 5750673 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0881. Min Range: -7.0881
Max Act: 7.0256. Min Act: -0.1700
Data Index: 6578031 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0881. Min Range: -7.0881
Max Act: 7.0256. Min Act: -0.1700
Data Index: 8007106 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0881. Min Range: -7.0881
Max Act: 6.9631. Min Act: -0.1700
Data Index: 4728146 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0881. Min Range: -7.0881
Max Act: 6.9631. Min Act: -0.1700
Data Index: 1486740 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0881. Min Range: -7.0881
Max Act: 6.9319. Min Act: -0.1700
Data Index: 8686183 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0881. Min Range: -7.0881
Max Act: 6.9006. Min Act: -0.1700
Data Index: 3094834 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0881. Min Range: -7.0881
Max Act: 6.8694. Min Act: -0.1700
Data Index: 5582561 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0881. Min Range: -7.0881
Max Act: 6.8069. Min Act: -0.1700
Data Index: 373466 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0881. Min Range: -7.0881
Max Act: 6.8694. Min Act: -0.1700
Data Index: 2046901 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0881. Min Range: -7.0881
Max Act: 6.7756. Min Act: -0.1700
Data Index: 5462325 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0881. Min Range: -7.0881
Max Act: 6.7131. Min Act: -0.1700
Data Index: 1998160 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0881. Min Range: -7.0881
Max Act: 6.7131. Min Act: -0.1700
Data Index: 4588532 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0881. Min Range: -7.0881
Max Act: 6.7131. Min Act: -0.1700
Data Index: 988949 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0881. Min Range: -7.0881
Max Act: 6.7444. Min Act: -0.1700
Data Index: 1250859 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0881. Min Range: -7.0881
Max Act: 6.7756. Min Act: -0.1700
Data Index: 3378105 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0881. Min Range: -7.0881
Max Act: 6.7131. Min Act: -0.1700
Data Index: 5761702 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0881. Min Range: -7.0881
Max Act: 6.6194. Min Act: -0.1700
Data Index: 7209996 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0881. Min Range: -7.0881
Max Act: 6.7131. Min Act: -0.1700
Data Index: 6704585 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19