Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 63 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0652. Min Range: -6.0652
Max Act: 6.0652. Min Act: -0.1700
Data Index: 1607056 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.9402. Min Act: -0.1700
Data Index: 3514514 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.9714. Min Act: -0.1700
Data Index: 8169851 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.8464. Min Act: -0.1700
Data Index: 7530770 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.7839. Min Act: -0.1700
Data Index: 2255140 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.7214. Min Act: -0.1700
Data Index: 1330341 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.7214. Min Act: -0.1700
Data Index: 3909150 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.7214. Min Act: -0.1700
Data Index: 134618 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.6902. Min Act: -0.1700
Data Index: 7584550 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.6589. Min Act: -0.1700
Data Index: 1418310 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.6902. Min Act: -0.1700
Data Index: 2587077 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.5964. Min Act: -0.1700
Data Index: 2922703 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.5964. Min Act: -0.1700
Data Index: 4880451 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.6589. Min Act: -0.1700
Data Index: 7318162 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.6277. Min Act: -0.1700
Data Index: 6333762 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.5964. Min Act: -0.1700
Data Index: 1830179 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.5964. Min Act: -0.1700
Data Index: 3492602 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.5339. Min Act: -0.1700
Data Index: 847329 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.5652. Min Act: -0.1700
Data Index: 4076946 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0652. Min Range: -6.0652
Max Act: 5.5652. Min Act: -0.1700
Data Index: 2795945 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19