Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3129 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2484. Min Range: -3.2484
Max Act: 3.2484. Min Act: -0.1700
Data Index: 1981255 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2484. Min Range: -3.2484
Max Act: 3.2484. Min Act: -0.1700
Data Index: 8609778 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2484. Min Range: -3.2484
Max Act: 3.2484. Min Act: -0.1700
Data Index: 6686309 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2484. Min Range: -3.2484
Max Act: 3.2484. Min Act: -0.1700
Data Index: 8071471 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2484. Min Range: -3.2484
Max Act: 3.2484. Min Act: -0.1700
Data Index: 597468 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2484. Min Range: -3.2484
Max Act: 3.2484. Min Act: -0.1700
Data Index: 423961 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2484. Min Range: -3.2484
Max Act: 3.2484. Min Act: -0.1700
Data Index: 7660609 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2484. Min Range: -3.2484
Max Act: 3.2484. Min Act: -0.1700
Data Index: 2313652 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2484. Min Range: -3.2484
Max Act: 2.9964. Min Act: -0.1700
Data Index: 6813731 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2484. Min Range: -3.2484
Max Act: 2.9964. Min Act: -0.1700
Data Index: 7667924 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2484. Min Range: -3.2484
Max Act: 2.9964. Min Act: -0.1700
Data Index: 1640479 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2484. Min Range: -3.2484
Max Act: 2.9964. Min Act: -0.1700
Data Index: 603090 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2484. Min Range: -3.2484
Max Act: 2.9964. Min Act: -0.1700
Data Index: 6490988 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2484. Min Range: -3.2484
Max Act: 2.9964. Min Act: -0.1700
Data Index: 5014050 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2484. Min Range: -3.2484
Max Act: 2.9964. Min Act: -0.1700
Data Index: 393532 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2484. Min Range: -3.2484
Max Act: 2.9964. Min Act: -0.1700
Data Index: 8161951 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2484. Min Range: -3.2484
Max Act: 2.9964. Min Act: -0.1700
Data Index: 1954123 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2484. Min Range: -3.2484
Max Act: 2.9964. Min Act: -0.1700
Data Index: 6639422 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2484. Min Range: -3.2484
Max Act: 2.9647. Min Act: -0.1700
Data Index: 8631971 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2484. Min Range: -3.2484
Max Act: 2.9489. Min Act: -0.1700
Data Index: 870926 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19