Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1591 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4112. Min Range: -6.4112
Max Act: 6.4112. Min Act: -0.1700
Data Index: 2517147 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4112. Min Range: -6.4112
Max Act: 6.3174. Min Act: -0.1700
Data Index: 3884183 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4112. Min Range: -6.4112
Max Act: 6.2862. Min Act: -0.1700
Data Index: 7360840 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4112. Min Range: -6.4112
Max Act: 6.1612. Min Act: -0.1700
Data Index: 816377 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4112. Min Range: -6.4112
Max Act: 6.1612. Min Act: -0.1700
Data Index: 7670566 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4112. Min Range: -6.4112
Max Act: 6.0362. Min Act: -0.1700
Data Index: 6399436 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4112. Min Range: -6.4112
Max Act: 6.0674. Min Act: -0.1700
Data Index: 4350120 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4112. Min Range: -6.4112
Max Act: 6.0362. Min Act: -0.1700
Data Index: 6948549 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4112. Min Range: -6.4112
Max Act: 6.0362. Min Act: -0.1700
Data Index: 3633582 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4112. Min Range: -6.4112
Max Act: 6.0049. Min Act: -0.1700
Data Index: 7632567 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4112. Min Range: -6.4112
Max Act: 5.9737. Min Act: -0.1700
Data Index: 6646513 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4112. Min Range: -6.4112
Max Act: 5.9424. Min Act: -0.1700
Data Index: 6031084 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4112. Min Range: -6.4112
Max Act: 5.9424. Min Act: -0.1700
Data Index: 7397189 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4112. Min Range: -6.4112
Max Act: 5.9737. Min Act: -0.1700
Data Index: 2696801 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4112. Min Range: -6.4112
Max Act: 5.9424. Min Act: -0.1700
Data Index: 5312974 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4112. Min Range: -6.4112
Max Act: 5.9112. Min Act: -0.1700
Data Index: 304085 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4112. Min Range: -6.4112
Max Act: 5.9424. Min Act: -0.1700
Data Index: 3313871 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4112. Min Range: -6.4112
Max Act: 5.9112. Min Act: -0.1700
Data Index: 4128871 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4112. Min Range: -6.4112
Max Act: 5.9112. Min Act: -0.1700
Data Index: 7918265 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4112. Min Range: -6.4112
Max Act: 5.8799. Min Act: -0.1700
Data Index: 1883250 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19