Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1268 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.6356. Min Act: -0.1700
Data Index: 6985040 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.3856. Min Act: -0.1700
Data Index: 5099015 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.3543. Min Act: -0.1700
Data Index: 4692027 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.2606. Min Act: -0.1700
Data Index: 6326590 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.2293. Min Act: -0.1700
Data Index: 7119552 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.2293. Min Act: -0.1700
Data Index: 6786945 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1981. Min Act: -0.1700
Data Index: 7619314 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1981. Min Act: -0.1700
Data Index: 7188829 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1668. Min Act: -0.1700
Data Index: 7807229 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1668. Min Act: -0.1700
Data Index: 6687781 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1668. Min Act: -0.1700
Data Index: 2207652 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1668. Min Act: -0.1700
Data Index: 5099014 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1356. Min Act: -0.1700
Data Index: 3999765 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1356. Min Act: -0.1700
Data Index: 1218027 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1043. Min Act: -0.1700
Data Index: 1237147 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.0731. Min Act: -0.1700
Data Index: 4254036 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.0731. Min Act: -0.1700
Data Index: 3396561 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.0418. Min Act: -0.1700
Data Index: 5101913 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.0106. Min Act: -0.1700
Data Index: 5099022 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.0418. Min Act: -0.1700
Data Index: 3342711 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19