Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.6964. Min Act: -0.1700
Data Index: 7252311 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.6652. Min Act: -0.1700
Data Index: 6846544 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.6652. Min Act: -0.1700
Data Index: 4602355 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.6339. Min Act: -0.1700
Data Index: 2626129 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.6339. Min Act: -0.1700
Data Index: 6846542 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.6339. Min Act: -0.1700
Data Index: 7744802 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.6027. Min Act: -0.1700
Data Index: 5794518 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.6339. Min Act: -0.1700
Data Index: 3023012 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.5714. Min Act: -0.1700
Data Index: 4602354 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.5089. Min Act: -0.1700
Data Index: 2373533 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.5402. Min Act: -0.1700
Data Index: 5314202 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.5402. Min Act: -0.1700
Data Index: 5875022 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.5402. Min Act: -0.1700
Data Index: 3023014 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.5089. Min Act: -0.1700
Data Index: 2148224 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.5089. Min Act: -0.1700
Data Index: 4411305 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.4777. Min Act: -0.1700
Data Index: 302292 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.5089. Min Act: -0.1700
Data Index: 3023013 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.4777. Min Act: -0.1700
Data Index: 5875027 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.4777. Min Act: -0.1700
Data Index: 4525963 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6964. Min Range: -5.6964
Max Act: 5.4464. Min Act: -0.1700
Data Index: 4521319 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19