Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3116 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.5622. Min Act: -0.1700
Data Index: 154596 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.4997. Min Act: -0.1700
Data Index: 1210249 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.4997. Min Act: -0.1700
Data Index: 4221264 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.4684. Min Act: -0.1700
Data Index: 2538182 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.4372. Min Act: -0.1700
Data Index: 2261313 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.4059. Min Act: -0.1700
Data Index: 7700192 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.4059. Min Act: -0.1700
Data Index: 7574349 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.4059. Min Act: -0.1700
Data Index: 3192652 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.3747. Min Act: -0.1700
Data Index: 5526217 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.3747. Min Act: -0.1700
Data Index: 2402802 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.3434. Min Act: -0.1700
Data Index: 5983027 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.3434. Min Act: -0.1700
Data Index: 5885945 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.3122. Min Act: -0.1700
Data Index: 2499084 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.3747. Min Act: -0.1700
Data Index: 3177738 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.3434. Min Act: -0.1700
Data Index: 8625060 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.3434. Min Act: -0.1700
Data Index: 2272949 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.3122. Min Act: -0.1700
Data Index: 1271862 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.3434. Min Act: -0.1700
Data Index: 3952473 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.3122. Min Act: -0.1700
Data Index: 807657 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5622. Min Range: -5.5622
Max Act: 5.3122. Min Act: -0.1700
Data Index: 8116732 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19