Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2505 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.4153. Min Act: -0.1700
Data Index: 8617684 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.3528. Min Act: -0.1700
Data Index: 1264674 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.2278. Min Act: -0.1700
Data Index: 8665081 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.1966. Min Act: -0.1700
Data Index: 4175246 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.1653. Min Act: -0.1700
Data Index: 4672389 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.1341. Min Act: -0.1700
Data Index: 4475473 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.1341. Min Act: -0.1700
Data Index: 5887179 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.1341. Min Act: -0.1700
Data Index: 8455432 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.1028. Min Act: -0.1700
Data Index: 2455005 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.1341. Min Act: -0.1700
Data Index: 5970657 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.1028. Min Act: -0.1700
Data Index: 5435432 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.1028. Min Act: -0.1700
Data Index: 683236 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.1028. Min Act: -0.1700
Data Index: 8401497 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.0716. Min Act: -0.1700
Data Index: 4633167 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.1028. Min Act: -0.1700
Data Index: 3064423 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.0716. Min Act: -0.1700
Data Index: 2560399 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.0403. Min Act: -0.1700
Data Index: 8436122 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.0403. Min Act: -0.1700
Data Index: 8060641 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.0091. Min Act: -0.1700
Data Index: 4724597 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4153. Min Range: -5.4153
Max Act: 5.0091. Min Act: -0.1700
Data Index: 3182202 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19