Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.8138. Min Act: -0.1700
Data Index: 2778820 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.7825. Min Act: -0.1700
Data Index: 3437712 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.5950. Min Act: -0.1700
Data Index: 5264351 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.5325. Min Act: -0.1700
Data Index: 6523419 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.5638. Min Act: -0.1700
Data Index: 3516582 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.5638. Min Act: -0.1700
Data Index: 508434 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.5013. Min Act: -0.1700
Data Index: 2954196 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.5013. Min Act: -0.1700
Data Index: 3556836 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.4700. Min Act: -0.1700
Data Index: 6627986 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.3763. Min Act: -0.1700
Data Index: 2918505 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.4388. Min Act: -0.1700
Data Index: 7661776 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.4388. Min Act: -0.1700
Data Index: 5378996 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.3763. Min Act: -0.1700
Data Index: 7572458 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.4388. Min Act: -0.1700
Data Index: 8358634 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.3763. Min Act: -0.1700
Data Index: 1913750 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.3450. Min Act: -0.1700
Data Index: 3307435 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.3763. Min Act: -0.1700
Data Index: 5508755 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.3763. Min Act: -0.1700
Data Index: 2102302 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.3763. Min Act: -0.1700
Data Index: 8323267 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8138. Min Range: -5.8138
Max Act: 5.3450. Min Act: -0.1700
Data Index: 1637442 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19