Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1972 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.4175. Min Act: -0.1700
Data Index: 4954398 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.2613. Min Act: -0.1700
Data Index: 519594 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.1988. Min Act: -0.1700
Data Index: 628006 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.2300. Min Act: -0.1700
Data Index: 6950246 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.1988. Min Act: -0.1700
Data Index: 6287611 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.1988. Min Act: -0.1700
Data Index: 8618038 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.1988. Min Act: -0.1700
Data Index: 1344166 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.1988. Min Act: -0.1700
Data Index: 2810318 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.1363. Min Act: -0.1700
Data Index: 7097333 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.1675. Min Act: -0.1700
Data Index: 1223062 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.1363. Min Act: -0.1700
Data Index: 845195 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.0738. Min Act: -0.1700
Data Index: 420117 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.1050. Min Act: -0.1700
Data Index: 182608 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.1363. Min Act: -0.1700
Data Index: 7480704 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.1050. Min Act: -0.1700
Data Index: 5432534 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.0738. Min Act: -0.1700
Data Index: 6197878 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.0425. Min Act: -0.1700
Data Index: 891503 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.1363. Min Act: -0.1700
Data Index: 6522027 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.0738. Min Act: -0.1700
Data Index: 2182507 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4175. Min Range: -5.4175
Max Act: 5.0113. Min Act: -0.1700
Data Index: 5357064 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19