Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2417 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.9304. Min Act: -0.1700
Data Index: 811300 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8991. Min Act: -0.1700
Data Index: 1854040 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8991. Min Act: -0.1700
Data Index: 4866155 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8678. Min Act: -0.1700
Data Index: 2066024 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8678. Min Act: -0.1700
Data Index: 966074 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8678. Min Act: -0.1700
Data Index: 3451841 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8678. Min Act: -0.1700
Data Index: 1178140 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8366. Min Act: -0.1700
Data Index: 99956 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8366. Min Act: -0.1700
Data Index: 1476420 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8366. Min Act: -0.1700
Data Index: 7285940 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8366. Min Act: -0.1700
Data Index: 3617259 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8366. Min Act: -0.1700
Data Index: 7032209 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8366. Min Act: -0.1700
Data Index: 354951 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8366. Min Act: -0.1700
Data Index: 1160511 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8366. Min Act: -0.1700
Data Index: 2500310 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8366. Min Act: -0.1700
Data Index: 311575 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8366. Min Act: -0.1700
Data Index: 3959144 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8366. Min Act: -0.1700
Data Index: 1787467 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8053. Min Act: -0.1700
Data Index: 1462163 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9304. Min Range: -3.9304
Max Act: 3.8053. Min Act: -0.1700
Data Index: 646218 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19