Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3690 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.4622. Min Act: -0.1662
Data Index: 7669632 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.4622. Min Act: -0.1700
Data Index: 295115 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.4476. Min Act: -0.1683
Data Index: 1849801 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.4259. Min Act: -0.1697
Data Index: 1993383 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.3974. Min Act: -0.1700
Data Index: 6069776 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.4045. Min Act: -0.1700
Data Index: 7132961 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.3904. Min Act: -0.1676
Data Index: 676471 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.3834. Min Act: -0.1700
Data Index: 4808123 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.3834. Min Act: -0.1700
Data Index: 6305445 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.3764. Min Act: -0.1700
Data Index: 6425106 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.3695. Min Act: -0.1700
Data Index: 4467980 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.3764. Min Act: -0.1662
Data Index: 6465169 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.3626. Min Act: -0.1700
Data Index: 4217448 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.3557. Min Act: -0.1699
Data Index: 7210691 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.3557. Min Act: -0.1700
Data Index: 4589208 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.3489. Min Act: -0.1669
Data Index: 6425107 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.3489. Min Act: -0.1700
Data Index: 8261325 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.3489. Min Act: -0.1700
Data Index: 1499720 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.3489. Min Act: -0.1697
Data Index: 4860592 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4622. Min Range: -0.4622
Max Act: 0.3489. Min Act: -0.1700
Data Index: 6631430 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19