Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2400 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.7487. Min Act: -0.1700
Data Index: 1800575 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.6705. Min Act: -0.1700
Data Index: 8246109 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.5766. Min Act: -0.1700
Data Index: 5576908 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.5766. Min Act: -0.1700
Data Index: 5252806 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.5452. Min Act: -0.1700
Data Index: 3639599 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.5452. Min Act: -0.1700
Data Index: 4597127 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.5139. Min Act: -0.1700
Data Index: 1564966 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.5139. Min Act: -0.1700
Data Index: 3636851 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.5139. Min Act: -0.1700
Data Index: 6333025 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.4983. Min Act: -0.1700
Data Index: 5707564 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.4826. Min Act: -0.1700
Data Index: 5168588 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.4826. Min Act: -0.1700
Data Index: 8018638 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.4669. Min Act: -0.1700
Data Index: 3147524 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.4669. Min Act: -0.1700
Data Index: 3253291 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.4513. Min Act: -0.1700
Data Index: 3895811 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.4513. Min Act: -0.1700
Data Index: 682251 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.4513. Min Act: -0.1700
Data Index: 2022623 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.4513. Min Act: -0.1700
Data Index: 6578150 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.4356. Min Act: -0.1700
Data Index: 362616 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7487. Min Range: -3.7487
Max Act: 3.4356. Min Act: -0.1700
Data Index: 2828559 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19