Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1503 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.6138. Min Act: -0.1700
Data Index: 4336214 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.6138. Min Act: -0.1700
Data Index: 2310093 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.5825. Min Act: -0.1700
Data Index: 3545106 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.6138. Min Act: -0.1700
Data Index: 4785769 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.6138. Min Act: -0.1700
Data Index: 8393962 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.5200. Min Act: -0.1700
Data Index: 1542113 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.5200. Min Act: -0.1700
Data Index: 2539593 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.5825. Min Act: -0.1700
Data Index: 1997887 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.5513. Min Act: -0.1700
Data Index: 138313 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.5200. Min Act: -0.1700
Data Index: 4460383 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.4888. Min Act: -0.1700
Data Index: 4807439 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.4888. Min Act: -0.1700
Data Index: 643867 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.4888. Min Act: -0.1700
Data Index: 2962626 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.4888. Min Act: -0.1700
Data Index: 5122373 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.4575. Min Act: -0.1700
Data Index: 4578844 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.4575. Min Act: -0.1700
Data Index: 241261 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.4263. Min Act: -0.1700
Data Index: 470016 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.3950. Min Act: -0.1700
Data Index: 4363730 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.3950. Min Act: -0.1700
Data Index: 5338971 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6138. Min Range: -5.6138
Max Act: 5.3950. Min Act: -0.1700
Data Index: 267514 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19