Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 785 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3360. Min Range: -9.3360
Max Act: 9.3360. Min Act: -0.1700
Data Index: 4390000 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3360. Min Range: -9.3360
Max Act: 9.2110. Min Act: -0.1700
Data Index: 8808285 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3360. Min Range: -9.3360
Max Act: 9.2110. Min Act: -0.1700
Data Index: 1804953 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3360. Min Range: -9.3360
Max Act: 9.1485. Min Act: -0.1700
Data Index: 2236080 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3360. Min Range: -9.3360
Max Act: 9.1485. Min Act: -0.1700
Data Index: 7549184 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3360. Min Range: -9.3360
Max Act: 9.0860. Min Act: -0.1700
Data Index: 855317 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3360. Min Range: -9.3360
Max Act: 9.0860. Min Act: -0.1700
Data Index: 3640464 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3360. Min Range: -9.3360
Max Act: 9.0860. Min Act: -0.1700
Data Index: 3501297 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3360. Min Range: -9.3360
Max Act: 9.0235. Min Act: -0.1700
Data Index: 3365807 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3360. Min Range: -9.3360
Max Act: 9.0235. Min Act: -0.1700
Data Index: 4820585 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3360. Min Range: -9.3360
Max Act: 9.0235. Min Act: -0.1700
Data Index: 2468512 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3360. Min Range: -9.3360
Max Act: 9.0235. Min Act: -0.1700
Data Index: 2011680 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3360. Min Range: -9.3360
Max Act: 9.0235. Min Act: -0.1700
Data Index: 1463991 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3360. Min Range: -9.3360
Max Act: 8.9610. Min Act: -0.1700
Data Index: 2574699 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3360. Min Range: -9.3360
Max Act: 9.0235. Min Act: -0.1700
Data Index: 5123641 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3360. Min Range: -9.3360
Max Act: 8.9610. Min Act: -0.1700
Data Index: 8552921 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3360. Min Range: -9.3360
Max Act: 9.0235. Min Act: -0.1700
Data Index: 1110766 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3360. Min Range: -9.3360
Max Act: 8.8985. Min Act: -0.1700
Data Index: 1318004 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3360. Min Range: -9.3360
Max Act: 8.9610. Min Act: -0.1700
Data Index: 1907811 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3360. Min Range: -9.3360
Max Act: 8.8985. Min Act: -0.1700
Data Index: 955807 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19