Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 97 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.2881. Min Act: -0.1700
Data Index: 4671070 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.2256. Min Act: -0.1700
Data Index: 402683 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.2256. Min Act: -0.1700
Data Index: 6851548 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.1943. Min Act: -0.1700
Data Index: 500889 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.1943. Min Act: -0.1700
Data Index: 73047 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.1943. Min Act: -0.1700
Data Index: 1986016 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.1631. Min Act: -0.1700
Data Index: 7037486 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.1631. Min Act: -0.1700
Data Index: 7892811 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.1631. Min Act: -0.1700
Data Index: 7528009 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.1318. Min Act: -0.1700
Data Index: 5469061 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.1006. Min Act: -0.1700
Data Index: 1274273 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.1006. Min Act: -0.1700
Data Index: 5793969 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.1006. Min Act: -0.1700
Data Index: 1218281 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.1006. Min Act: -0.1700
Data Index: 7258169 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.1006. Min Act: -0.1700
Data Index: 797329 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.0693. Min Act: -0.1700
Data Index: 6050482 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.0693. Min Act: -0.1700
Data Index: 3054319 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.0693. Min Act: -0.1700
Data Index: 3120263 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.0693. Min Act: -0.1700
Data Index: 6270209 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2881. Min Range: -6.2881
Max Act: 6.0693. Min Act: -0.1700
Data Index: 3708960 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19