Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.4578. Min Act: -0.1700
Data Index: 948347 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.3599. Min Act: -0.1700
Data Index: 6019893 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.3435. Min Act: -0.1700
Data Index: 8745730 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.3435. Min Act: -0.1700
Data Index: 8630019 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.3435. Min Act: -0.1700
Data Index: 8456570 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.3271. Min Act: -0.1699
Data Index: 2194429 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.3271. Min Act: -0.1700
Data Index: 4866667 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.3271. Min Act: -0.1700
Data Index: 840812 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.3271. Min Act: -0.1700
Data Index: 4007454 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.2778. Min Act: -0.1700
Data Index: 633294 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.3107. Min Act: -0.1700
Data Index: 510769 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.2942. Min Act: -0.1700
Data Index: 2451207 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.2942. Min Act: -0.1700
Data Index: 897391 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.2778. Min Act: -0.1700
Data Index: 7535772 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.2778. Min Act: -0.1700
Data Index: 5883161 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.2778. Min Act: -0.1700
Data Index: 6037508 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.2778. Min Act: -0.1700
Data Index: 7157189 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.2778. Min Act: -0.1700
Data Index: 6400139 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.2778. Min Act: -0.1700
Data Index: 1653312 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4578. Min Range: -2.4578
Max Act: 2.2778. Min Act: -0.1700
Data Index: 1653307 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19