Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3301 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0380. Min Range: -11.0380
Max Act: 11.0380. Min Act: -0.1700
Data Index: 2680008 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0380. Min Range: -11.0380
Max Act: 10.6005. Min Act: -0.1700
Data Index: 2238428 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0380. Min Range: -11.0380
Max Act: 10.4755. Min Act: -0.1700
Data Index: 2040215 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0380. Min Range: -11.0380
Max Act: 10.3505. Min Act: -0.1699
Data Index: 3158039 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0380. Min Range: -11.0380
Max Act: 10.3505. Min Act: -0.1693
Data Index: 8450063 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0380. Min Range: -11.0380
Max Act: 10.1630. Min Act: -0.1700
Data Index: 3482725 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0380. Min Range: -11.0380
Max Act: 10.1630. Min Act: -0.1697
Data Index: 6734503 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0380. Min Range: -11.0380
Max Act: 10.1005. Min Act: -0.1700
Data Index: 2145066 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0380. Min Range: -11.0380
Max Act: 10.0380. Min Act: -0.1700
Data Index: 3151990 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0380. Min Range: -11.0380
Max Act: 9.9755. Min Act: -0.1699
Data Index: 8333277 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0380. Min Range: -11.0380
Max Act: 9.9130. Min Act: -0.1700
Data Index: 8189230 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0380. Min Range: -11.0380
Max Act: 9.9130. Min Act: -0.1700
Data Index: 229267 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0380. Min Range: -11.0380
Max Act: 9.9130. Min Act: -0.1699
Data Index: 8031862 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0380. Min Range: -11.0380
Max Act: 9.8505. Min Act: -0.1699
Data Index: 4344014 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0380. Min Range: -11.0380
Max Act: 9.9130. Min Act: -0.1700
Data Index: 7709563 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0380. Min Range: -11.0380
Max Act: 9.7880. Min Act: -0.1700
Data Index: 2307744 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0380. Min Range: -11.0380
Max Act: 9.7255. Min Act: -0.1699
Data Index: 2391390 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0380. Min Range: -11.0380
Max Act: 9.7880. Min Act: -0.1700
Data Index: 5247369 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0380. Min Range: -11.0380
Max Act: 9.7880. Min Act: -0.1700
Data Index: 3021762 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0380. Min Range: -11.0380
Max Act: 9.7880. Min Act: -0.1700
Data Index: 2567927 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19