Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1976 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.4159. Min Act: -0.1700
Data Index: 5131602 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.3847. Min Act: -0.1700
Data Index: 8157631 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.3847. Min Act: -0.1700
Data Index: 1806648 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.3534. Min Act: -0.1700
Data Index: 7711306 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.3222. Min Act: -0.1700
Data Index: 8692257 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.3222. Min Act: -0.1700
Data Index: 4733389 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.2597. Min Act: -0.1700
Data Index: 7098046 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.2597. Min Act: -0.1700
Data Index: 3438171 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.2597. Min Act: -0.1700
Data Index: 468749 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.2284. Min Act: -0.1700
Data Index: 4776463 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.1972. Min Act: -0.1700
Data Index: 5130448 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.1659. Min Act: -0.1700
Data Index: 2832895 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.1659. Min Act: -0.1700
Data Index: 6085464 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.1659. Min Act: -0.1700
Data Index: 1961728 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.1034. Min Act: -0.1700
Data Index: 877268 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.1034. Min Act: -0.1700
Data Index: 4341063 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.1034. Min Act: -0.1700
Data Index: 4658493 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.0722. Min Act: -0.1700
Data Index: 1539392 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.0722. Min Act: -0.1700
Data Index: 5641546 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4159. Min Range: -5.4159
Max Act: 5.0722. Min Act: -0.1700
Data Index: 4452694 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19