Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3792 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1668. Min Range: -7.1668
Max Act: 7.1668. Min Act: -0.1700
Data Index: 4213140 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1668. Min Range: -7.1668
Max Act: 7.0418. Min Act: -0.1700
Data Index: 8595184 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.9480. Min Act: -0.1700
Data Index: 2424559 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.8855. Min Act: -0.1700
Data Index: 8038700 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.8543. Min Act: -0.1700
Data Index: 883416 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.8543. Min Act: -0.1700
Data Index: 2066507 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.7918. Min Act: -0.1700
Data Index: 6670734 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.7605. Min Act: -0.1700
Data Index: 4587749 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.7293. Min Act: -0.1700
Data Index: 8394444 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.7293. Min Act: -0.1700
Data Index: 5264410 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.6980. Min Act: -0.1700
Data Index: 3692652 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.7293. Min Act: -0.1700
Data Index: 3651047 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.6980. Min Act: -0.1700
Data Index: 4169546 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.6668. Min Act: -0.1700
Data Index: 3632056 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.6668. Min Act: -0.1700
Data Index: 7158516 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.6355. Min Act: -0.1700
Data Index: 4713750 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.6355. Min Act: -0.1700
Data Index: 6860865 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.6668. Min Act: -0.1700
Data Index: 6305992 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.6355. Min Act: -0.1700
Data Index: 8762126 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1668. Min Range: -7.1668
Max Act: 6.6043. Min Act: -0.1700
Data Index: 7205140 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19