Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 547 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1700
Data Index: 609449 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1700
Data Index: 7237062 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.5535. Min Act: -0.1700
Data Index: 5317708 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.5535. Min Act: -0.1700
Data Index: 5469840 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.5535. Min Act: -0.1700
Data Index: 4259735 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.5223. Min Act: -0.1700
Data Index: 706114 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.4598. Min Act: -0.1700
Data Index: 7870517 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.4910. Min Act: -0.1700
Data Index: 7423908 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.4910. Min Act: -0.1700
Data Index: 6825483 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.4598. Min Act: -0.1700
Data Index: 7546165 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.4285. Min Act: -0.1700
Data Index: 1476348 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.3973. Min Act: -0.1700
Data Index: 4437766 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.3973. Min Act: -0.1700
Data Index: 1670023 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.3973. Min Act: -0.1700
Data Index: 2363390 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.3973. Min Act: -0.1700
Data Index: 963048 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.3660. Min Act: -0.1700
Data Index: 431426 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.3660. Min Act: -0.1700
Data Index: 1531428 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.3973. Min Act: -0.1700
Data Index: 8163984 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.3660. Min Act: -0.1700
Data Index: 209750 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.3348. Min Act: -0.1700
Data Index: 3535249 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19