Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2423 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.3399. Min Act: -0.1695
Data Index: 1033358 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.3046. Min Act: -0.1693
Data Index: 4622411 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2870. Min Act: -0.1700
Data Index: 7099357 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2605. Min Act: -0.1698
Data Index: 4328834 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2605. Min Act: -0.1655
Data Index: 6150842 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2605. Min Act: -0.1696
Data Index: 2350615 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2517. Min Act: -0.1698
Data Index: 3785275 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2517. Min Act: -0.1640
Data Index: 5714748 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2429. Min Act: -0.1640
Data Index: 1637661 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2517. Min Act: -0.1700
Data Index: 3750084 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2429. Min Act: -0.1700
Data Index: 5605388 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2429. Min Act: -0.1700
Data Index: 6484670 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2517. Min Act: -0.1692
Data Index: 2047465 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2429. Min Act: -0.1700
Data Index: 4089044 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2517. Min Act: -0.1599
Data Index: 1365131 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2341. Min Act: -0.1682
Data Index: 4683081 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2429. Min Act: -0.1691
Data Index: 4677531 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2341. Min Act: -0.1700
Data Index: 3823614 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2429. Min Act: -0.1673
Data Index: 3118771 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3399. Min Range: -1.3399
Max Act: 1.2341. Min Act: -0.1681
Data Index: 4008500 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19